© 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
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 31694
    Prev
    Next
    INDEX
    Explanations

    descriptions of inventions

    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
    ishop
    -0.07
    573
    -0.06
     součas
    -0.06
     beaten
    -0.06
    Serial
    -0.06
     repay
    -0.06
    ECH
    -0.06
    -wave
    -0.06
     Glory
    -0.06
    分布
    -0.06
    POSITIVE LOGITS
    .dateTimePicker
    0.08
     scarf
    0.07
    _ORD
    0.07
    ...↵↵↵
    0.07
    .glide
    0.07
    (fr
    0.07
    ...,
    0.06
     deadline
    0.06
    =↵
    0.06
    METHOD
    0.06
    Activations Density 0.183%

    No Known Activations