© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 118688
    Prev
    Next
    INDEX
    Explanations

    code fragments

    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
    lined
    -0.07
    ioneer
    -0.06
     Democratic
    -0.06
    пос
    -0.06
     Democracy
    -0.06
     speakers
    -0.06
    away
    -0.06
    *=
    -0.06
     stale
    -0.06
    cdc
    -0.06
    POSITIVE LOGITS
    ιών
    0.07
    _dt
    0.06
     Theory
    0.06
    _override
    0.06
    jur
    0.06
     тай
    0.06
    matcher
    0.06
    þ
    0.06
    Orientation
    0.06
     Maison
    0.06
    Activations Density 0.020%

    No Known Activations