© 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. 91484
    Prev
    Next
    INDEX
    Explanations

    :

    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
     dof
    -0.07
     het
    -0.06
     pastoral
    -0.06
     начале
    -0.06
     inning
    -0.06
     cez
    -0.06
    那个
    -0.06
     disponible
    -0.06
    _clr
    -0.06
     unidades
    -0.06
    POSITIVE LOGITS
     minValue
    0.08
    rypto
    0.07
    _target
    0.07
    Url
    0.07
    Received
    0.07
    decision
    0.06
     Ranked
    0.06
    getActiveSheet
    0.06
    parameter
    0.06
    .vol
    0.06
    Activations Density 0.023%

    No Known Activations