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. 41817
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
     Claus
    -0.07
     Derrick
    -0.07
    侧
    -0.06
    안마
    -0.06
    th
    -0.06
    Constraints
    -0.06
     IID
    -0.06
    .bo
    -0.06
     alarm
    -0.06
    *c
    -0.06
    POSITIVE LOGITS
     ,
    0.07
     kamu
    0.06
     "('
    0.06
     dua
    0.06
     Selbst
    0.06
    _ml
    0.06
     Hệ
    0.06
    _Pl
    0.06
     بعضی
    0.06
    :expr
    0.06
    Activations Density 0.181%

    No Known Activations