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. 43447
    Prev
    Next
    INDEX
    Explanations

    references to events in historical timelines

    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
     yacc
    -0.06
    isin
    -0.06
    ush
    -0.06
    ytic
    -0.06
    yst
    -0.06
    _nb
    -0.06
    ircuit
    -0.06
     Rowe
    -0.06
    onte
    -0.06
     Doom
    -0.06
    POSITIVE LOGITS
    eh
    0.12
    ahl
    0.11
    ried
    0.10
    ör
    0.10
    ür
    0.09
    ahlen
    0.09
    ug
    0.09
    ö
    0.09
    annt
    0.09
    rist
    0.09
    Activations Density 0.003%

    No Known Activations