© 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. 19-RESID-POST-AA
    11. 71056
    Prev
    Next
    INDEX
    Explanations

    ,

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     savvy
    -0.07
    canf
    -0.07
    Lastly
    -0.07
     Geological
    -0.07
    ])){↵
    -0.06
    'use
    -0.06
    Hash
    -0.06
    ")){↵
    -0.06
    den
    -0.06
     raging
    -0.06
    POSITIVE LOGITS
    >Action
    0.07
    ITT
    0.07
    ISH
    0.06
    419
    0.06
     tuning
    0.06
     生命周期
    0.06
     Lightning
    0.06
     OSS
    0.06
     Changed
    0.06
    ish
    0.06
    Activations Density 0.000%

    No Known Activations