© 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. 11-RESID-POST-AA
    6. 105362
    Prev
    Next
    INDEX
    Explanations

    what

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Candidate
    -0.07
    scopes
    -0.07
     initials
    -0.06
    _candidate
    -0.06
    dden
    -0.06
     gerektir
    -0.06
    -LAST
    -0.06
     hrs
    -0.06
     runaway
    -0.06
    (camera
    -0.06
    POSITIVE LOGITS
    .','
    0.07
    getPage
    0.07
    _integration
    0.06
    anteed
    0.06
     khai
    0.06
    erb
    0.06
    棋牌
    0.06
    ("---
    0.06
    اغ
    0.06
     hypoth
    0.06
    Activations Density 0.030%

    No Known Activations