© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 130122
    Prev
    Next
    INDEX
    Explanations

    fuel

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Arrest
    -0.07
     jailed
    -0.07
     taraf
    -0.07
    aversal
    -0.06
     cont
    -0.06
     Literal
    -0.06
     또는
    -0.06
    rase
    -0.06
     talent
    -0.06
    ँ
    -0.06
    POSITIVE LOGITS
     уд
    0.07
    .Charting
    0.07
     Sodium
    0.06
     Elli
    0.06
     sodium
    0.06
    §Ã
    0.06
    號
    0.06
    .bid
    0.06
     px
    0.06
     Indicates
    0.06
    Activations Density 0.002%

    No Known Activations