Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 55624
    Prev
    Next
    INDEX
    Explanations

    line

    np_max-act · gemini-2.0-flash

    This neuron selectively activates on technical, domain-specific terms (especially hyphenated or compound keywords) common in engineering and networking contexts.

    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
     antib
    -0.07
     loyalty
    -0.06
    にと
    -0.06
     있던
    -0.06
     orderby
    -0.06
     своих
    -0.06
     миним
    -0.06
     sous
    -0.06
     extracted
    -0.06
    _mix
    -0.06
    POSITIVE LOGITS
     Humph
    0.07
    Gets
    0.07
    raz
    0.06
     Üst
    0.06
    ini
    0.06
    _facebook
    0.06
     TCL
    0.06
    SN
    0.06
    Bon
    0.06
    Medical
    0.06
    Activations Density 0.058%

    No Known Activations