© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 92637
    Prev
    Next
    INDEX
    Explanations

    Console

    np_max-act · gemini-2.0-flash

    The neuron fires on tokens that begin with an uppercase letter (i.e. capitalized words).

    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
    >>>>>>>>
    -0.08
     آقای
    -0.07
     INSERT
    -0.06
     дек
    -0.06
     naw
    -0.06
    lek
    -0.06
    -how
    -0.06
    follower
    -0.06
     trenches
    -0.06
     är
    -0.06
    POSITIVE LOGITS
     Vivo
    0.07
     Alias
    0.07
     Qualcomm
    0.07
    “.
    0.06
     courageous
    0.06
    ورية
    0.06
    觀
    0.06
    {*
    0.06
    sey
    0.06
     Vancouver
    0.06
    Activations Density 0.078%

    No Known Activations