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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 93472
    Prev
    Next
    INDEX
    Explanations

    Power management

    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
    rowad
    -0.07
    řik
    -0.07
    .Camera
    -0.07
    /we
    -0.06
     voj
    -0.06
    ’den
    -0.06
    Cha
    -0.06
    (custom
    -0.06
    enan
    -0.06
     Gaza
    -0.06
    POSITIVE LOGITS
     nab
    0.06
     carving
    0.06
     asynchronous
    0.06
    !==
    0.06
     статті
    0.06
     #↵
    0.06
     averaged
    0.06
    ¼
    0.06
    нерг
    0.06
    **:
    0.06
    Activations Density 0.007%

    No Known Activations