© 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
    7. Resid Post - 131k
    9. 27-RESID-POST-AA
    11. 60340
    Prev
    Next
    INDEX
    Explanations

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    edeyse
    -0.07
    ilename
    -0.07
    ERGY
    -0.07
    öy
    -0.07
    いる
    -0.07
    :::/
    -0.06
    bits
    -0.06
     lệ
    -0.06
     servicio
    -0.06
     Iter
    -0.06
    POSITIVE LOGITS
    lox
    0.07
    calloc
    0.06
     ermög
    0.06
    牌
    0.06
    (hour
    0.06
     \'
    0.06
     United
    0.06
    —one
    0.06
    .RemoveAt
    0.06
     Pistons
    0.05
    Activations Density 0.010%

    No Known Activations