© 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 EvalsExportsinterp-engineNEWAPI 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. 39654
    Prev
    Next
    INDEX
    Explanations

    mathematical terminology and concepts related to equations and functions

    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
     squash
    -0.07
    >Returns
    -0.07
     Beng
    -0.07
    ÅĻad
    -0.07
    ortal
    -0.07
    squ
    -0.06
     squ
    -0.06
    SSIP
    -0.06
    Float
    -0.06
     Garten
    -0.06
    POSITIVE LOGITS
     prime
    0.10
    gcd
    0.10
     gcd
    0.09
     primes
    0.09
    ç´ł
    0.08
     Prime
    0.08
    prime
    0.08
    Prime
    0.07
     prim
    0.07
    amage
    0.07
    Activations Density 0.058%

    No Known Activations