© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 55838
    Prev
    Next
    INDEX
    Explanations

    references to healthcare events and initiatives

    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
    ewood
    -0.08
    chio
    -0.07
    rell
    -0.07
     funeral
    -0.07
     Funeral
    -0.06
    /*č↵
    -0.06
     Ens
    -0.06
    uckets
    -0.06
    аÑĢам
    -0.06
     Erect
    -0.06
    POSITIVE LOGITS
     held
    0.09
    held
    0.08
    yp
    0.07
     %"
    0.07
    inspace
    0.07
    -held
    0.07
     entitled
    0.07
    bor
    0.06
     titled
    0.06
    iem
    0.06
    Activations Density 0.025%

    No Known Activations