© 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. 119030
    Prev
    Next
    INDEX
    Explanations

    variables and functions related to mathematical computations or operations

    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
    sterol
    -0.08
    sez
    -0.07
     sprav
    -0.07
     moda
    -0.07
    agens
    -0.07
    eyh
    -0.07
    odcast
    -0.07
     sice
    -0.07
     ninh
    -0.07
    memberof
    -0.07
    POSITIVE LOGITS
     likewise
    0.07
     dit
    0.06
    ode
    0.06
     distinct
    0.06
     =
    0.06
     ;↵↵
    0.06
     Dit
    0.06
     Pill
    0.05
    alm
    0.05
     .↵↵
    0.05
    Activations Density 0.052%

    No Known Activations