© 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. 15-RESID-POST-AA
    11. 115310
    Prev
    Next
    INDEX
    Explanations

    accelerate

    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
     참고
    -0.08
     restaur
    -0.08
    variant
    -0.07
     variable
    -0.06
     sexy
    -0.06
     understanding
    -0.06
    -mini
    -0.06
    (Activity
    -0.06
     resta
    -0.06
     Britann
    -0.06
    POSITIVE LOGITS
    &utm
    0.06
    AT
    0.06
    .githubusercontent
    0.06
    room
    0.06
     DL
    0.06
     рей
    0.06
    _PTR
    0.06
    IRS
    0.06
    utorials
    0.06
    〜
    0.06
    Activations Density 0.009%

    No Known Activations