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. 16208
    Prev
    Next
    INDEX
    Explanations

    SVG

    np_max-act · gemini-2.0-flash

    This neuron activates on mentions of SVG markup or elements (e.g. “SVG”, “svg”) in the text.

    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
    findOne
    -0.06
    Snow
    -0.06
    Reducers
    -0.06
    sert
    -0.06
     멀
    -0.06
    |required
    -0.06
    CX
    -0.06
    .Dimension
    -0.06
    =pd
    -0.05
    _pv
    -0.05
    POSITIVE LOGITS
    fic
    0.07
     Q
    0.07
    ラン
    0.07
     adjusting
    0.06
    chron
    0.06
    런
    0.06
     WW
    0.06
    ayı
    0.06
     Conj
    0.06
    ôm
    0.06
    Activations Density 0.021%

    No Known Activations