© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 44413
    Prev
    Next
    INDEX
    Explanations

    /vnd

    np_max-act · gemini-2.0-flash

    words related to file handling and document processing in programming contexts.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron spots occurrences of the vendor‐specific MIME subtype “vnd.microsoft.icon” (e.g. in image/vnd.microsoft.icon declarations).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .say
    -0.07
    输
    -0.07
     Cleans
    -0.06
    WASHINGTON
    -0.06
    oped
    -0.06
    f
    -0.06
    Bone
    -0.06
    	RTLU
    -0.06
     ساخته
    -0.06
     pies
    -0.06
    POSITIVE LOGITS
    /apps
    0.08
     Çok
    0.06
    viar
    0.06
     comprehend
    0.06
    thern
    0.06
     Bulg
    0.06
    /************************************************************************************************
    0.06
    //================================================================
    0.06
     pov
    0.06
     //@
    0.06
    Activations Density 0.002%

    No Known Activations