© 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. 7-RESID-POST-AA
    11. 58137
    Prev
    Next
    INDEX
    Explanations

    code

    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
    _MAXIMUM
    -0.07
    -delete
    -0.07
    _SUPER
    -0.07
    <|begin_of_text|>
    -0.06
     Modal
    -0.06
    ================================================
    -0.06
    .manager
    -0.06
    .Export
    -0.06
     message
    -0.06
    -password
    -0.06
    POSITIVE LOGITS
     Grass
    0.07
    ightly
    0.06
    lij
    0.06
    Fun
    0.06
    řet
    0.06
     �
    0.06
     Garn
    0.06
    stm
    0.06
     turtles
    0.06
    ंर
    0.06
    Activations Density 0.030%

    No Known Activations