© 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. 11-RESID-POST-AA
    11. 12693
    Prev
    Next
    INDEX
    Explanations

    Prohibitions and restrictions

    np_max-act · gemini-2.0-flash

    The neuron detects language expressing legal prohibitions or bans—especially restrictions on owning or having contact with animals or other entities.

    oai_token-act-pair · o4-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
     SEXP
    -0.07
     issuer
    -0.06
    _SESSION
    -0.06
     psychiat
    -0.06
    —with
    -0.06
     duct
    -0.06
    \uD
    -0.06
    роме
    -0.06
    ngr
    -0.06
     MPU
    -0.06
    POSITIVE LOGITS
    .CenterScreen
    0.07
    طن
    0.06
    ^
    0.06
     Tune
    0.06
    стати
    0.06
    range
    0.06
    ponder
    0.06
     �
    0.06
    oined
    0.06
    สำเร
    0.06
    Activations Density 0.009%

    No Known Activations