Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 11-RESID-POST-AA
    6. 78498
    Prev
    Next
    INDEX
    Explanations

    Products

    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_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
    eat
    -0.07
    ETY
    -0.07
     Sar
    -0.07
    .tick
    -0.06
    Depth
    -0.06
     pol
    -0.06
    iate
    -0.06
    mes
    -0.06
    sWith
    -0.06
    pref
    -0.06
    POSITIVE LOGITS
     kullanım
    0.08
     hexadecimal
    0.07
    .getMessage
    0.07
     edilmiş
    0.07
     seçim
    0.07
    /rfc
    0.07
     ∀
    0.07
    ,{↵
    0.06
     очеред
    0.06
     edildi
    0.06
    Activations Density 0.028%

    No Known Activations