© 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. 118602
    Prev
    Next
    INDEX
    Explanations

    Author names/initials

    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
    processed
    -0.08
     Machines
    -0.08
    Machine
    -0.08
    Mode
    -0.07
    -in
    -0.07
    FieldValue
    -0.07
     Wolfe
    -0.07
    -end
    -0.07
     folding
    -0.07
     되
    -0.07
    POSITIVE LOGITS
     domin
    0.07
    Statics
    0.06
    .updated
    0.06
    .modal
    0.06
    /Desktop
    0.06
    ominator
    0.06
     Medicare
    0.06
     """
↵
↵
    0.06
    呼ば
    0.06
     근
    0.06
    Activations Density 0.025%

    No Known Activations