© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 27-RESID-POST-AA
    11. 20317
    Prev
    Next
    INDEX
    Explanations

    say "namespace"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fac
    -0.07
    Jamie
    -0.07
     Society
    -0.07
    .chunk
    -0.07
    586
    -0.06
    信用
    -0.06
     hardships
    -0.06
    imson
    -0.06
    )
↵
↵
↵
    -0.06
     captains
    -0.06
    POSITIVE LOGITS
     /*
    0.08
     vigilant
    0.07
     الت
    0.06
    과
    0.06
     avail
    0.06
    ouce
    0.06
    _RGCTX
    0.06
    }}{{
    0.06
    _settings
    0.06
     sucesso
    0.06
    Activations Density 0.004%

    No Known Activations