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. 11-RESID-POST-AA
    6. 86042
    Prev
    Next
    INDEX
    Explanations

    quotation mark

    np_max-act · gemini-2.0-flash

    The neuron fires on the JSON “repository” object’s `"type"` field (e.g. `"type": "git"`) in package‐style manifest files.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bazı
    -0.07
    "
    -0.07
     lol
    -0.07
     algum
    -0.06
     depths
    -0.06
    ığ
    -0.06
    clo
    -0.06
    jiště
    -0.06
    mph
    -0.06
    jiang
    -0.06
    POSITIVE LOGITS
    /fwlink
    0.06
    _softmax
    0.06
    <String
    0.06
     درباره
    0.06
     коман
    0.06
    =item
    0.06
     (("
    0.06
     اين
    0.06
     '';
    0.06
    全面
    0.06
    Activations Density 0.001%

    No Known Activations