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. 85876
    Prev
    Next
    INDEX
    Explanations

    Retrieving information

    np_max-act · gemini-2.0-flash

    The neuron responds to numeric tokens and date‐like sequences (digits, years, and related punctuation).

    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
    *=*=
    -0.07
     Distrib
    -0.07
    Failure
    -0.06
    346
    -0.06
    amenti
    -0.06
    :@"%
    -0.06
    016
    -0.06
    elapsed
    -0.06
    南省
    -0.06
     forKey
    -0.06
    POSITIVE LOGITS
    /el
    0.07
     ดาว
    0.06
    [input
    0.06
     nous
    0.06
     imperialism
    0.06
    _prod
    0.06
    '=>
    0.06
    Iterator
    0.06
     تصو
    0.06
     intrigue
    0.06
    Activations Density 0.003%

    No Known Activations