© 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
    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. 125148
    Prev
    Next
    INDEX
    Explanations

    legal and official matters

    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
    933
    -0.08
     میدان
    -0.07
     Very
    -0.07
     trauma
    -0.06
     full
    -0.06
     EUR
    -0.06
     Imag
    -0.06
    itude
    -0.06
     receptors
    -0.06
     temple
    -0.06
    POSITIVE LOGITS
     tablesp
    0.07
    .Msg
    0.07
    <string
    0.07
     Belediyesi
    0.07
     HMAC
    0.06
     período
    0.06
    اهی
    0.06
    扬
    0.06
    +=(
    0.06
     kilomet
    0.06
    Activations Density 0.152%

    No Known Activations