Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 22-LLAMASCOPE-RES-131K
    6. 5700
    Prev
    Next
    INDEX
    Explanations

    references to large companies and complex projects

    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
    ichen
    -0.08
    اÙĪ
    -0.07
    chluss
    -0.07
    341
    -0.07
    dden
    -0.07
    171
    -0.06
     ç§ĭ
    -0.06
    è°±
    -0.06
    iband
    -0.06
    arden
    -0.06
    POSITIVE LOGITS
    tip
    0.06
    MIC
    0.06
    nts
    0.06
    requ
    0.06
    ÑĮко
    0.06
     Reid
    0.06
    REA
    0.06
     INCIDENT
    0.06
    lement
    0.06
    isku
    0.06
    Activations Density 0.006%

    No Known Activations