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. 15-RESID-POST-AA
    6. 21245
    Prev
    Next
    INDEX
    Explanations

    :

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Door
    -0.07
    话
    -0.06
     LV
    -0.06
    _extra
    -0.06
    んな
    -0.06
    &M
    -0.06
    Square
    -0.06
    records
    -0.06
     servisi
    -0.06
     Tribute
    -0.06
    POSITIVE LOGITS
    }")↵↵
    0.08
    ('\
    0.06
     ]↵↵
    0.06
    (PyObject
    0.06
    よう
    0.06
     kern
    0.06
    iloc
    0.06
    ,cv
    0.06
    ');↵↵↵
    0.06
     Michele
    0.06
    Activations Density 0.010%

    No Known Activations