© 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. 87401
    Prev
    Next
    INDEX
    Explanations

    fl

    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
     روی
    -0.06
    谋
    -0.06
    !***
    -0.06
     　　　　　　　　　
    -0.06
     IU
    -0.06
    ()\
    -0.06
     Liv
    -0.06
    ']?>
    -0.06
     compress
    -0.06
     ／:
    -0.06
    POSITIVE LOGITS
     καὶ
    0.08
    िकट
    0.07
    _forms
    0.06
     Nä
    0.06
     FL
    0.06
    "default
    0.06
    .blogspot
    0.06
     multit
    0.06
    /effects
    0.06
     voksne
    0.06
    Activations Density 0.011%

    No Known Activations