© 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. 87763
    Prev
    Next
    INDEX
    Explanations

    terms related to medical treatments and conditions

    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
    ita
    -0.10
    ito
    -0.09
    ali
    -0.09
    itos
    -0.09
    ed
    -0.09
    es
    -0.09
    al
    -0.08
    itel
    -0.08
    sch
    -0.08
    tain
    -0.08
    POSITIVE LOGITS
    fty
    0.09
    coln
    0.09
    cola
    0.09
    ÑĮко
    0.07
    ergic
    0.07
    sha
    0.07
    ascimento
    0.07
    shaw
    0.07
    omial
    0.07
    burgh
    0.07
    Activations Density 0.170%

    No Known Activations