© 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. 78605
    Prev
    Next
    INDEX
    Explanations

    programming syntax and structure elements

    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
     LAN
    -0.07
    -0.06
    teri
    -0.06
     Tod
    -0.06
    ils
    -0.06
    ieu
    -0.06
    .hwp
    -0.06
    ž
    -0.06
    978
    -0.06
     ç¼
    -0.06
    POSITIVE LOGITS
    adlo
    0.07
    coli
    0.07
     rowspan
    0.07
    ãĥ©ãĥĥãĤ¯
    0.06
    uat
    0.06
    _GF
    0.06
    ãĥĨãĥ«
    0.06
    Occurrences
    0.06
    olle
    0.06
    _bridge
    0.06
    Activations Density 0.023%

    No Known Activations