© 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
    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. 103620
    Prev
    Next
    INDEX
    Explanations

    that

    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
    لان
    -0.06
    osg
    -0.06
    丘
    -0.06
    ])(
    -0.06
    úmer
    -0.06
     Estimated
    -0.06
     výše
    -0.06
    Workspace
    -0.06
     çevre
    -0.06
    shaw
    -0.06
    POSITIVE LOGITS
    endon
    0.07
     kWh
    0.07
     sniff
    0.07
     hype
    0.06
    >a
    0.06
     Decorating
    0.06
    _detalle
    0.06
     Beh
    0.06
    盛
    0.06
     madre
    0.06
    Activations Density 0.051%

    No Known Activations