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. 84680
    Prev
    Next
    INDEX
    Explanations

    nth term in a sequence

    np_max-act · gemini-2.0-flash

    The neuron fires on the fractional (“decimal‐point”) portions of numbers in these sequences.

    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
     billig
    -0.06
    лой
    -0.06
    _TD
    -0.06
    каж
    -0.06
     сохра
    -0.06
    χι
    -0.06
     Labels
    -0.06
    :image
    -0.05
    TEAM
    -0.05
     asign
    -0.05
    POSITIVE LOGITS
     (){↵
    0.08
    <src
    0.07
    ोषण
    0.07
    "},
    ↵
    0.07
     css
    0.07
    ǐ
    0.07
    狀
    0.07
     sắc
    0.07
     BufferedWriter
    0.07
    YSIS
    0.06
    Activations Density 0.027%

    No Known Activations