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. 34971
    Prev
    Next
    INDEX
    Explanations

    cytok

    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
    ceries
    -0.07
     Finch
    -0.07
    пион
    -0.07
    payment
    -0.07
    caffe
    -0.06
    -cond
    -0.06
     ESC
    -0.06
     Dairy
    -0.06
     encryption
    -0.06
    _pop
    -0.06
    POSITIVE LOGITS
    Browse
    0.07
    tim
    0.06
     sympathetic
    0.06
     mines
    0.06
    /Edit
    0.06
    不要
    0.06
     Lua
    0.06
     vyk
    0.06
    :NS
    0.06
    osph
    0.06
    Activations Density 0.014%

    No Known Activations