Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 15-RESID-POST-AA
    6. 4901
    Prev
    Next
    INDEX
    Explanations

    set

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Datas
    -0.06
     TimeInterval
    -0.06
    корист
    -0.06
    .Route
    -0.06
     		
    -0.06
    softmax
    -0.06
     Tire
    -0.06
    рати
    -0.06
    _literal
    -0.06
    sigmoid
    -0.06
    POSITIVE LOGITS
     set
    0.09
     setting
    0.08
     sets
    0.07
     memorable
    0.07
    CHR
    0.07
    ți
    0.07
     Boh
    0.07
    .Set
    0.06
    ZERO
    0.06
    amy
    0.06
    Activations Density 0.068%

    No Known Activations