© 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. 29618
    Prev
    Next
    INDEX
    Explanations

    scientific terminology and phrases related to cancer research and treatment mechanisms

    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
    abus
    -0.08
    orate
    -0.06
    erli
    -0.06
     Magn
    -0.06
    kem
    -0.06
    832
    -0.06
     layers
    -0.06
    gebra
    -0.06
    Singleton
    -0.06
     meg
    -0.06
    POSITIVE LOGITS
     addCriterion
    0.08
     пÑĢоÑĤе
    0.07
     Prote
    0.07
     Ala
    0.07
    огод
    0.07
     prote
    0.07
    ADX
    0.07
    CLUDED
    0.07
    RIA
    0.07
     Bannon
    0.07
    Activations Density 0.023%

    No Known Activations