© 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. 7-RESID-POST-AA
    11. 5390
    Prev
    Next
    INDEX
    Explanations

    Awards

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ционные
    -0.07
    ・・
    -0.07
     پیشنهاد
    -0.07
    My
    -0.07
    �
    -0.06
    adolu
    -0.06
    ир
    -0.06
     TW
    -0.06
    ывает
    -0.06
    、ア
    -0.06
    POSITIVE LOGITS
     harbour
    0.08
    <User
    0.06
    iminal
    0.06
    <Cell
    0.06
    <location
    0.06
     tvar
    0.06
    fills
    0.06
    -moving
    0.06
    .listener
    0.06
     denies
    0.06
    Activations Density 0.391%

    No Known Activations