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. 84224
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
     다음과
    -0.07
     eventual
    -0.07
    getInstance
    -0.06
     LayoutInflater
    -0.06
     Charity
    -0.06
    ия
    -0.06
     gathered
    -0.06
     Messages
    -0.06
     conversions
    -0.06
     deleted
    -0.06
    POSITIVE LOGITS
    pone
    0.09
    CF
    0.07
    pad
    0.07
     Encode
    0.07
     flattened
    0.07
    (hit
    0.07
     persone
    0.06
     时
    0.06
    _fe
    0.06
    pline
    0.06
    Activations Density 0.001%

    No Known Activations