© 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. 29647
    Prev
    Next
    INDEX
    Explanations

    references to genuine or significant items or concepts

    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
    ling
    -0.06
    гал
    -0.06
    voje
    -0.06
    aku
    -0.06
    oro
    -0.06
    igs
    -0.06
     miscellaneous
    -0.06
    /bind
    -0.05
     esl
    -0.05
    ongo
    -0.05
    POSITIVE LOGITS
     ones
    0.13
     thereof
    0.11
    ones
    0.10
     version
    0.10
     versions
    0.10
    version
    0.09
    çīĪæľ¬
    0.09
     examples
    0.08
     Ones
    0.08
     Versions
    0.08
    Activations Density 0.062%

    No Known Activations