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. 19-RESID-POST-AA
    6. 9941
    Prev
    Next
    INDEX
    Explanations

    some

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wanna
    -0.07
     ос
    -0.06
     pasar
    -0.06
    _json
    -0.06
    γ
    -0.06
    -lg
    -0.06
     初
    -0.06
    격
    -0.06
     getImage
    -0.06
    _ori
    -0.06
    POSITIVE LOGITS
     BusinessException
    0.07
     Grad
    0.07
    _dup
    0.06
     그
    0.06
    лата
    0.06
    paragus
    0.06
    (environment
    0.06
    ählt
    0.06
     Wayback
    0.06
    ibBundleOrNil
    0.06
    Activations Density 0.058%

    No Known Activations