© 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. 15-LLAMASCOPE-RES-131K
    11. 89983
    Prev
    Next
    INDEX
    Explanations

    scientific paper reference numbers

    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
    Pragma
    -0.08
    st
    -0.08
    Å¡ti
    -0.07
    acomment
    -0.07
    enda
    -0.07
    stor
    -0.07
    egis
    -0.07
    inery
    -0.06
    urer
    -0.06
    rud
    -0.06
    POSITIVE LOGITS
     Wash
    0.07
    velt
    0.06
     poster
    0.06
     Gors
    0.06
    poster
    0.06
    æī
    0.06
    ConnectionFactory
    0.06
     wash
    0.06
    ikal
    0.06
    <path
    0.06
    Activations Density 0.049%

    No Known Activations