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. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 96116
    Prev
    Next
    INDEX
    Explanations

    references to comic book companies or creators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ife
    -0.06
    [
    -0.06
    iddle
    -0.05
    ire
    -0.05
    ^
    -0.05
    anger
    -0.05
    _regularizer
    -0.05
    est
    -0.05
    rosse
    -0.05
     Raum
    -0.05
    POSITIVE LOGITS
    fromJson
    0.09
    /loose
    0.08
    GBK
    0.07
    è̳
    0.07
    çĤī
    0.07
    림
    0.07
    _FT
    0.07
    -logo
    0.07
    pcf
    0.07
    æĿIJ
    0.07
    Activations Density 0.003%

    No Known Activations