© 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. 9-LLAMASCOPE-RES-131K
    11. 95562
    Prev
    Next
    INDEX
    Explanations

    code-related syntax patterns and structure

    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
    ettel
    -0.06
    rapper
    -0.06
    /apis
    -0.06
    andy
    -0.06
     fold
    -0.06
     Sug
    -0.06
     Ard
    -0.06
    peria
    -0.06
    irs
    -0.06
     bulletin
    -0.06
    POSITIVE LOGITS
    aska
    0.07
    rippling
    0.06
    ÄĽst
    0.06
    CharCode
    0.06
    alloca
    0.06
    áh
    0.06
    .try
    0.06
     oblig
    0.06
    _CSS
    0.06
    uesto
    0.06
    Activations Density 0.000%

    No Known Activations