© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 93267
    Prev
    Next
    INDEX
    Explanations

    Scientific studies/data

    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
    rias
    -0.07
     mystical
    -0.07
    โลย
    -0.07
    ierten
    -0.07
     الوص
    -0.07
     στρα
    -0.06
    lış
    -0.06
    /renderer
    -0.06
    otive
    -0.06
    iare
    -0.06
    POSITIVE LOGITS
    Spin
    0.07
    ehler
    0.06
     함수
    0.06
     Exiting
    0.06
    )-
    0.06
     Sport
    0.06
    }',
    0.06
    .shortcuts
    0.06
     pair
    0.06
    Angel
    0.06
    Activations Density 0.114%

    No Known Activations