© 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. 84168
    Prev
    Next
    INDEX
    Explanations

    content related to performance and artistic expression

    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
     territory
    -0.07
    tro
    -0.06
     territories
    -0.06
    bane
    -0.06
     tast
    -0.06
     stage
    -0.06
    Reusable
    -0.06
     Claw
    -0.06
     resource
    -0.06
    ¼
    -0.06
    POSITIVE LOGITS
    /watch
    0.09
     closely
    0.07
     ikt
    0.07
    705
    0.07
    swagen
    0.07
    _while
    0.07
     EXP
    0.07
    afort
    0.07
     attent
    0.07
    offee
    0.07
    Activations Density 0.023%

    No Known Activations