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. 40462
    Prev
    Next
    INDEX
    Explanations

    sqrt

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of the “sqrt(…)” token pattern, i.e. square‐root function calls.

    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
     forests
    -0.07
    hem
    -0.07
    iterr
    -0.07
    ーション
    -0.07
     مشهد
    -0.07
    ्द
    -0.06
    (layout
    -0.06
    _EXPORT
    -0.06
    nehmer
    -0.06
    ández
    -0.06
    POSITIVE LOGITS
    _feed
    0.08
     hỗ
    0.06
    Working
    0.06
    458
    0.06
    actices
    0.06
     lstm
    0.06
     TInt
    0.06
    /crypto
    0.05
    .loggedIn
    0.05
    ptime
    0.05
    Activations Density 0.003%

    No Known Activations