© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 5-LLAMASCOPE-RES-131K
    6. 126390
    Prev
    Next
    INDEX
    Explanations

    references to code functionality and execution

    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
    asma
    -0.07
    ÏĤ
    -0.06
    atter
    -0.06
    als
    -0.06
    strap
    -0.06
    uli
    -0.06
    anas
    -0.06
    bling
    -0.06
    aha
    -0.06
    iese
    -0.06
    POSITIVE LOGITS
    ISCO
    0.08
     Aç
    0.07
    locator
    0.07
     dilig
    0.07
    ÙĪØ©
    0.07
    uchar
    0.07
     ninh
    0.07
    ÃŃž
    0.07
    CLUD
    0.06
    thon
    0.06
    Activations Density 0.028%

    No Known Activations