© 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. 119129
    Prev
    Next
    INDEX
    Explanations

    elements related to microbiology and genetics

    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
    urum
    -0.06
    omers
    -0.06
    ISCO
    -0.06
     trấn
    -0.06
    å¡ļ
    -0.06
    ặn
    -0.06
     Milo
    -0.06
    elles
    -0.06
     or
    -0.06
    umbo
    -0.06
    POSITIVE LOGITS
     Ag
    0.11
     ag
    0.10
    Ag
    0.10
    ag
    0.10
    .ag
    0.09
    (ag
    0.09
    -ag
    0.09
    /ag
    0.09
    agnost
    0.08
    lag
    0.08
    Activations Density 0.021%

    No Known Activations