© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 76431
    Prev
    Next
    INDEX
    Explanations

    mathematical terms and expressions, particularly logarithmic and algebraic concepts

    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
     Tal
    -0.07
    ajas
    -0.06
    ifers
    -0.06
    окон
    -0.06
     Gle
    -0.06
     deduct
    -0.06
    ifer
    -0.06
    èĥ¶
    -0.06
    efs
    -0.06
    684
    -0.06
    POSITIVE LOGITS
    aeper
    0.07
    arma
    0.07
    ycastle
    0.07
    @nate
    0.07
     exponent
    0.07
    lama
    0.07
    .gc
    0.07
     log
    0.07
     exponential
    0.07
     Rear
    0.06
    Activations Density 0.034%

    No Known Activations