© 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. 106998
    Prev
    Next
    INDEX
    Explanations

    references to biochemical quantities and concentrations

    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
    239
    -0.06
    /loose
    -0.06
    unya
    -0.06
     wings
    -0.06
    itou
    -0.06
    /XML
    -0.06
    ucus
    -0.06
    emez
    -0.06
    _PLACE
    -0.06
    ÑıÑģ
    -0.06
    POSITIVE LOGITS
     quantities
    0.12
     amounts
    0.12
     doses
    0.11
     quantity
    0.10
     concentrations
    0.09
     proportions
    0.09
     sufficient
    0.09
    amount
    0.08
     amount
    0.08
     levels
    0.07
    Activations Density 0.045%

    No Known Activations