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. 21393
    Prev
    Next
    INDEX
    Explanations

    code

    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
     penetration
    -0.07
    _with
    -0.06
    _order
    -0.06
    attack
    -0.06
    .Sprite
    -0.06
     ONLY
    -0.06
     onc
    -0.06
     bizarre
    -0.06
    .GetOrdinal
    -0.06
    _Syntax
    -0.06
    POSITIVE LOGITS
     RTL
    0.07
    نجليزية
    0.07
    (Logger
    0.06
     Vis
    0.06
    ED
    0.06
    ES
    0.06
    classifier
    0.06
    TINGS
    0.06
     جمهور
    0.06
    ắt
    0.06
    Activations Density 0.030%

    No Known Activations