© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 121663
    Prev
    Next
    INDEX
    Explanations

    Formal documents

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     真
    -0.07
    "*
    -0.07
    /new
    -0.07
    ง
    -0.06
     law
    -0.06
    _information
    -0.06
    knowledge
    -0.06
    。，
    -0.06
    -INFRINGEMENT
    -0.06
    bracht
    -0.06
    POSITIVE LOGITS
    .compat
    0.06
    scrollTop
    0.06
    _App
    0.06
    .LayoutParams
    0.06
    CancelButton
    0.06
    ableViewController
    0.06
    .unsqueeze
    0.05
     Terraria
    0.05
     RAID
    0.05
    isson
    0.05
    Activations Density 0.645%

    No Known Activations