© 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. 103593
    Prev
    Next
    INDEX
    Explanations

    references to celestial bodies or objects in space

    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
    ÙIJب
    -0.07
    ctp
    -0.06
     Boeh
    -0.06
     Arap
    -0.06
    θεν
    -0.06
    immel
    -0.06
    znik
    -0.06
    Щ
    -0.06
    æŃ©
    -0.06
    ocator
    -0.06
    POSITIVE LOGITS
    andi
    0.08
    æŁĵ
    0.06
    urb
    0.06
     Tam
    0.06
     mA
    0.06
    ache
    0.06
     Julien
    0.06
     ============================================================================↵
    0.06
    _ENGINE
    0.05
    plusplus
    0.05
    Activations Density 0.006%

    No Known Activations