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. 85262
    Prev
    Next
    INDEX
    Explanations

    (name

    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
    channel
    -0.07
    -string
    -0.06
    ;↵
    -0.06
     Tul
    -0.06
     Raq
    -0.06
    undo
    -0.06
     EVEN
    -0.06
    patch
    -0.06
     interes
    -0.06
     Lama
    -0.06
    POSITIVE LOGITS
    (name
    0.09
     rode
    0.07
    /)
    0.06
     controversies
    0.06
     Rodr
    0.06
     mattresses
    0.06
    OffsetTable
    0.06
     refrigerator
    0.06
    宽
    0.06
    _VENDOR
    0.06
    Activations Density 0.001%

    No Known Activations