© 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. 91755
    Prev
    Next
    INDEX
    Explanations

    static

    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
    _is
    -0.07
    Steven
    -0.06
     Εξ
    -0.06
    tiles
    -0.06
    880
    -0.06
     Dod
    -0.06
    -normal
    -0.06
    .equal
    -0.06
    _TERMIN
    -0.06
    mol
    -0.05
    POSITIVE LOGITS
    ριστ
    0.08
     debate
    0.07
    .getUserName
    0.07
     geschichten
    0.06
    PROTO
    0.06
    _subject
    0.06
    .actions
    0.06
    isti
    0.06
     wrongful
    0.06
    CSI
    0.06
    Activations Density 0.004%

    No Known Activations