© 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. 55959
    Prev
    Next
    INDEX
    Explanations

    key terms related to health, medical procedures, and scientific measurements

    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
    uh
    -0.06
    iri
    -0.06
    æľºæŀĦ
    -0.06
    isi
    -0.06
    oven
    -0.06
    ystack
    -0.06
    ther
    -0.06
    riba
    -0.05
    assy
    -0.05
    Ãłm
    -0.05
    POSITIVE LOGITS
    icer
    0.08
    ılıç
    0.07
    ìĿ´íĦ°
    0.07
    AMESPACE
    0.07
    asca
    0.07
    esco
    0.07
    gnore
    0.07
    -related
    0.06
    ATO
    0.06
    gil
    0.06
    Activations Density 0.032%

    No Known Activations