© 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. 17443
    Prev
    Next
    INDEX
    Explanations

    mathematical concepts and conjectures

    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
     Sampler
    -0.07
    ÑĢаг
    -0.07
    verbatim
    -0.06
    æ²¢
    -0.06
     Muse
    -0.06
    æķ£
    -0.06
    quete
    -0.06
    ãĥ³ãĥĦ
    -0.06
    raction
    -0.06
    ibel
    -0.06
    POSITIVE LOGITS
     prime
    0.10
     Sie
    0.10
     primes
    0.10
     Prime
    0.10
    Prime
    0.09
     sieve
    0.09
     sie
    0.09
    prime
    0.08
     prim
    0.08
    _prime
    0.08
    Activations Density 0.051%

    No Known Activations