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. 79508
    Prev
    Next
    INDEX
    Explanations

    j

    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
     přibliž
    -0.06
    EF
    -0.06
     Frozen
    -0.06
     cheek
    -0.06
    -inner
    -0.06
     Press
    -0.06
     Mosul
    -0.06
    敷
    -0.06
     conducted
    -0.06
     Sinclair
    -0.06
    POSITIVE LOGITS
     花
    0.06
    productName
    0.06
    ikleri
    0.06
    odoxy
    0.06
    M
    0.06
    _PROM
    0.06
     MIX
    0.06
    crets
    0.06
    Alt
    0.06
     recognizing
    0.06
    Activations Density 0.003%

    No Known Activations