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. 31-LLAMASCOPE-RES-131K
    6. 43921
    Prev
    Next
    INDEX
    Explanations

    terms related to social partnerships and their activities

    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
    olik
    -0.07
     Gast
    -0.06
    ikal
    -0.06
     Gor
    -0.06
    /connection
    -0.06
    peg
    -0.06
     Junior
    -0.06
     wealth
    -0.06
    _HS
    -0.06
    วย
    -0.06
    POSITIVE LOGITS
     ou
    0.08
     proc
    0.08
     stat
    0.08
     either
    0.08
    :↵
    0.07
     tier
    0.07
     dilig
    0.07
     competent
    0.07
     OU
    0.07
    tier
    0.07
    Activations Density 0.012%

    No Known Activations