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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 93243
    Prev
    Next
    INDEX
    Explanations

    choose

    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
    779
    -0.07
    etzt
    -0.07
    M
    -0.07
     نسب
    -0.07
    /string
    -0.06
    verbatim
    -0.06
    ourcem
    -0.06
     Shader
    -0.06
    preter
    -0.06
     mop
    -0.06
    POSITIVE LOGITS
     pickerView
    0.07
    .cli
    0.07
     sz
    0.07
    (trigger
    0.06
     UICollectionViewCell
    0.06
    pok
    0.06
    ичний
    0.06
    .uint
    0.06
    _restore
    0.06
    aug
    0.06
    Activations Density 0.014%

    No Known Activations