© 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. 57723
    Prev
    Next
    INDEX
    Explanations

    comparative statements or phrases indicating frequency, quantity, or level of performance

    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
    esch
    -0.07
     sab
    -0.07
    ên
    -0.06
    tin
    -0.06
    sink
    -0.06
    oksen
    -0.06
    eron
    -0.06
     hã
    -0.06
    allery
    -0.06
     Khan
    -0.06
    POSITIVE LOGITS
     than
    0.11
    than
    0.09
     THAN
    0.09
     Than
    0.09
    -than
    0.09
    Than
    0.08
     než
    0.07
    _than
    0.07
    OPSIS
    0.07
     Fountain
    0.06
    Activations Density 0.066%

    No Known Activations