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. 74503
    Prev
    Next
    INDEX
    Explanations

    late

    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
     Relationships
    -0.06
    kj
    -0.06
     projections
    -0.06
     user
    -0.06
     shuffled
    -0.06
     fictional
    -0.06
    oll
    -0.06
     representations
    -0.06
    _dictionary
    -0.06
     PJ
    -0.06
    POSITIVE LOGITS
     late
    0.13
     Late
    0.11
    Late
    0.11
     pozdě
    0.07
    antine
    0.07
     CLOSE
    0.07
    amacare
    0.07
     Vance
    0.07
     Fare
    0.07
    Near
    0.07
    Activations Density 0.013%

    No Known Activations