© 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. 23-RESID-POST-AA
    11. 7728
    Prev
    Next
    INDEX
    Explanations

    say "-ysis ending"

    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_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     worker
    -0.06
    Feat
    -0.06
    ?"↵↵
    -0.06
     Legendary
    -0.06
     corpor
    -0.06
    .GetById
    -0.06
     );↵↵↵
    -0.06
    父亲
    -0.06
    [Any
    -0.06
    .baomidou
    -0.06
    POSITIVE LOGITS
    arah
    0.07
     include
    0.06
    �
    0.06
    يكا
    0.06
     первого
    0.06
     το
    0.06
    žení
    0.06
     náz
    0.06
    _ASS
    0.06
    ahkan
    0.06
    Activations Density 0.003%

    No Known Activations