© 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. 11-RESID-POST-AA
    11. 25764
    Prev
    Next
    INDEX
    Explanations

    Object

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    宿
    -0.07
     filetype
    -0.07
     xamarin
    -0.07
     blocked
    -0.06
     nues
    -0.06
    lle
    -0.06
    ,exports
    -0.06
     chron
    -0.06
     bì
    -0.06
    _TYP
    -0.06
    POSITIVE LOGITS
     baktı
    0.07
    통령
    0.07
     }}">{{
    0.06
     einmal
    0.06
     insensitive
    0.06
     puff
    0.06
    -cat
    0.06
    كوم
    0.06
     mẹ
    0.06
     Pan
    0.06
    Activations Density 0.282%

    No Known Activations