© 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. 19-RESID-POST-AA
    11. 87444
    Prev
    Next
    INDEX
    Explanations

    To be verb

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     survey
    -0.08
     COMM
    -0.07
     Survey
    -0.07
     elif
    -0.07
     endorse
    -0.07
     �
    -0.07
    essay
    -0.06
     Executes
    -0.06
    ))*(
    -0.06
     murm
    -0.06
    POSITIVE LOGITS
    /'+
    0.08
     wagon
    0.07
     pistol
    0.07
    Inspector
    0.07
    FileInfo
    0.06
    :UIButtonType
    0.06
     depreci
    0.06
    /"+
    0.06
    emodel
    0.06
    자를
    0.06
    Activations Density 0.093%

    No Known Activations