© 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. 26859
    Prev
    Next
    INDEX
    Explanations

    different forms of body-related terms and actions

    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
    Ñħодим
    -0.07
    ills
    -0.07
    ogan
    -0.07
    ushman
    -0.07
    ovat
    -0.07
    /files
    -0.07
    _totals
    -0.07
    ednou
    -0.07
    ın
    -0.06
     Whereas
    -0.06
    POSITIVE LOGITS
    -style
    0.07
    -type
    0.07
    âĢħ
    0.07
    ooter
    0.06
    alara
    0.06
    aea
    0.06
    imb
    0.06
    utorial
    0.06
    avra
    0.06
     [âĢ¦
    0.06
    Activations Density 0.042%

    No Known Activations