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. 15-RESID-POST-AA
    6. 10966
    Prev
    Next
    INDEX
    Explanations

    scientific research

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Nord
    -0.08
     letto
    -0.06
     simplement
    -0.06
     Hindi
    -0.06
     données
    -0.06
     niveau
    -0.06
     sequel
    -0.06
     контролю
    -0.06
     decentralized
    -0.06
     Committees
    -0.06
    POSITIVE LOGITS
    .Pos
    0.06
    .intent
    0.06
    ΟΝ
    0.06
    $L
    0.06
     -$
    0.06
     />
    0.06
    _guid
    0.06
     transplantation
    0.06
    Member
    0.06
     Prel
    0.05
    Activations Density 0.089%

    No Known Activations