© 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 (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 51816
    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
    Mutex
    -0.07
    .idx
    -0.07
     бак
    -0.06
    :"
    -0.06
    .Trace
    -0.06
     �
    -0.06
    fu
    -0.06
     regulated
    -0.06
    /docs
    -0.06
    ."),
    -0.06
    POSITIVE LOGITS
     permanent
    0.07
    vincia
    0.06
     Remove
    0.06
    coordinate
    0.06
     Laundry
    0.06
    Searching
    0.06
    Universal
    0.06
     Establishment
    0.06
     并
    0.06
    OURCE
    0.06
    Activations Density 0.003%

    No Known Activations