Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 86107
    Prev
    Next
    INDEX
    Explanations

    energy

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     美国
    -0.06
    он
    -0.06
    quiz
    -0.06
     paw
    -0.06
    .yy
    -0.06
     모르
    -0.06
    _obs
    -0.06
    _floor
    -0.06
    (insert
    -0.06
    emale
    -0.06
    POSITIVE LOGITS
     bf
    0.06
     begs
    0.06
     conform
    0.06
    chunks
    0.06
     gul
    0.06
    žít
    0.06
    abbr
    0.06
     veteran
    0.05
     chunks
    0.05
     dope
    0.05
    Activations Density 0.026%

    No Known Activations