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. 11-RESID-POST-AA
    6. 122807
    Prev
    Next
    INDEX
    Explanations

    (

    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
     Development
    -0.07
    versation
    -0.07
     Installed
    -0.07
    _NEG
    -0.06
     demon
    -0.06
     Arnold
    -0.06
    axis
    -0.06
     unspecified
    -0.06
     in
    -0.06
    emm
    -0.06
    POSITIVE LOGITS
    WithMany
    0.07
    ài
    0.07
    ‌پدی
    0.06
    acerb
    0.06
    .AutoScaleMode
    0.06
     daycare
    0.06
     settles
    0.06
    _FUNCTIONS
    0.06
    __;
    0.06
    Protected
    0.06
    Activations Density 0.010%

    No Known Activations