© 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. 11-RESID-POST-AA
    6. 20957
    Prev
    Next
    INDEX
    Explanations

    compass

    np_max-act · gemini-2.0-flash

    statements that express conditional reasoning or inferences based on observed characteristics.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cluster
    -0.07
    ahan
    -0.07
    _mount
    -0.06
     INA
    -0.06
     Fallon
    -0.06
    ),
    -0.06
    ITICAL
    -0.06
     Dublin
    -0.06
    ToLower
    -0.06
     wildly
    -0.06
    POSITIVE LOGITS
     боя
    0.07
    ilee
    0.07
    り
    0.07
    ью
    0.06
    óg
    0.06
    aturity
    0.06
     เม
    0.06
    ritten
    0.06
     编
    0.06
    *>(&
    0.06
    Activations Density 0.001%

    No Known Activations