© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 61359
    Prev
    Next
    INDEX
    Explanations

    code-related terms and structures

    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
    awe
    -0.07
     Nová
    -0.07
    istrat
    -0.07
    dda
    -0.07
    assi
    -0.07
    inja
    -0.07
    istringstream
    -0.07
    getDb
    -0.06
    anja
    -0.06
    Ymd
    -0.06
    POSITIVE LOGITS
     partial
    0.07
     read
    0.07
    Transfer
    0.07
    contin
    0.07
     transferred
    0.07
    /rss
    0.06
    transfer
    0.06
     transfer
    0.06
     Transfer
    0.06
     reading
    0.06
    Activations Density 0.044%

    No Known Activations