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. 50471
    Prev
    Next
    INDEX
    Explanations

    Programming

    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
    -basic
    -0.07
    Peace
    -0.06
    佐
    -0.06
    (ui
    -0.06
    .lines
    -0.06
     Syria
    -0.06
    βι
    -0.06
     capsule
    -0.06
     champions
    -0.06
     Channel
    -0.06
    POSITIVE LOGITS
     ̄
    0.06
    .deepEqual
    0.06
    тах
    0.06
    ισμός
    0.06
     conquer
    0.06
     tvrd
    0.06
     conson
    0.06
    :g
    0.06
    �断
    0.06
    _tables
    0.06
    Activations Density 0.051%

    No Known Activations