Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 93509
    Prev
    Next
    INDEX
    Explanations

    hexadecimal/alphanumeric IDs

    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
    collapsed
    -0.06
     �
    -0.06
    _BIN
    -0.06
     substitutes
    -0.06
    .foreach
    -0.06
     embarrassing
    -0.06
     합니다
    -0.06
     IRepository
    -0.06
     least
    -0.06
     Kelley
    -0.06
    POSITIVE LOGITS
    Rgb
    0.07
    lobal
    0.07
    OSH
    0.06
     tutto
    0.06
    Illustr
    0.06
    (pool
    0.06
     -----------
    0.06
    iou
    0.06
     Phi
    0.06
     centerY
    0.06
    Activations Density 0.020%

    No Known Activations