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. 7-RESID-POST-AA
    6. 119774
    Prev
    Next
    INDEX
    Explanations

    ables

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     shot
    -0.07
     agosto
    -0.06
     mature
    -0.06
     muchos
    -0.06
     maths
    -0.06
    捕
    -0.06
    _JO
    -0.06
     patterns
    -0.06
    >)↵
    -0.06
    -running
    -0.06
    POSITIVE LOGITS
    도록
    0.07
    �에
    0.07
     حي
    0.07
    iktig
    0.07
    ,strlen
    0.06
    ครบ
    0.06
     Accessories
    0.06
    něl
    0.06
    layout
    0.06
    invoice
    0.06
    Activations Density 0.008%

    No Known Activations