© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 69063
    Prev
    Next
    INDEX
    Explanations

    references to logarithmic functions or calculations

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    enaire
    -0.07
    ening
    -0.06
    @example
    -0.06
    argo
    -0.06
    lett
    -0.06
    ender
    -0.06
    wor
    -0.06
    States
    -0.06
    930
    -0.06
    enance
    -0.06
    POSITIVE LOGITS
    /log
    0.10
    arith
    0.09
    ued
    0.08
    ically
    0.08
    -log
    0.08
    istically
    0.07
    ALLY
    0.07
    ucz
    0.07
    ized
    0.07
    ometown
    0.07
    Activations Density 0.006%

    No Known Activations