© 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. 83994
    Prev
    Next
    INDEX
    Explanations

    anatomical terminology related to the human body

    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
    ForMember
    -0.07
    quential
    -0.07
    軽
    -0.07
    uky
    -0.06
    azo
    -0.06
    ilm
    -0.06
    stitial
    -0.06
    gesch
    -0.06
    iesta
    -0.06
    738
    -0.06
    POSITIVE LOGITS
     pars
    0.07
     Muscle
    0.06
     certif
    0.06
     unl
    0.06
     ---------------------------------------------------------------------------↵
    0.06
     Homo
    0.06
    اÙĦÛĮ
    0.06
    istr
    0.06
     trab
    0.06
     foss
    0.06
    Activations Density 0.013%

    No Known Activations