© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 21806
    Prev
    Next
    INDEX
    Explanations

    inserting/amending text

    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
     Ro
    -0.07
    Williams
    -0.07
    Su
    -0.06
    편
    -0.06
     باغ
    -0.06
     sez
    -0.06
    iba
    -0.06
    ディ
    -0.06
    νος
    -0.06
    озвращает
    -0.06
    POSITIVE LOGITS
    mighty
    0.07
     Rail
    0.07
     Coastal
    0.06
     Pyramid
    0.06
    058
    0.06
    GBT
    0.06
     Kia
    0.06
    atherine
    0.06
    hard
    0.06
     MemoryStream
    0.06
    Activations Density 0.003%

    No Known Activations