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. 11-RESID-POST-AA
    6. 84705
    Prev
    Next
    INDEX
    Explanations

    function/method/property

    np_max-act · gemini-2.0-flash

    The neuron never activates—i.e. it does not detect or respond to any token patterns.

    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
     supplement
    -0.07
     heating
    -0.07
     آر
    -0.07
    -depth
    -0.06
    (offset
    -0.06
     administrative
    -0.06
    arning
    -0.06
     aument
    -0.06
    (selection
    -0.06
    -focused
    -0.06
    POSITIVE LOGITS
    ptom
    0.07
    errick
    0.07
    编号
    0.06
    kn
    0.06
    urf
    0.06
     getRequest
    0.06
    _EXTERN
    0.06
    faker
    0.06
    &);↵↵
    0.06
    SIZE
    0.06
    Activations Density 0.039%

    No Known Activations