© 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. 120824
    Prev
    Next
    INDEX
    Explanations

    discussions about unresolved problems in mathematics and their complexity

    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
    orthand
    -0.07
     Zug
    -0.07
    ãĥ³ãĥģ
    -0.06
     Advantage
    -0.06
    ette
    -0.06
    fol
    -0.06
    NullOr
    -0.06
    ZR
    -0.06
    sov
    -0.06
     Dud
    -0.06
    POSITIVE LOGITS
     mystery
    0.09
     still
    0.08
     remains
    0.08
     remain
    0.08
     Remaining
    0.07
     remained
    0.07
     unsett
    0.07
     challenge
    0.07
     remaining
    0.07
     puzzle
    0.07
    Activations Density 0.023%

    No Known Activations