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. 30241
    Prev
    Next
    INDEX
    Explanations

    promoting

    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
     thousands
    -0.07
     Halk
    -0.06
     elements
    -0.06
     march
    -0.06
    ۲۰
    -0.06
    contenido
    -0.06
     domingo
    -0.06
     daleko
    -0.06
    ρ
    -0.06
    เง
    -0.06
    POSITIVE LOGITS
    айт
    0.07
    锦
    0.07
     вари
    0.06
    ollah
    0.06
     disadv
    0.06
    가는
    0.06
     manners
    0.06
     شه
    0.06
    ارات
    0.06
     квіт
    0.06
    Activations Density 0.032%

    No Known Activations