© 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. 86386
    Prev
    Next
    INDEX
    Explanations

    mathematical parameters and notations related to algorithms

    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
    dux
    -0.08
    edula
    -0.07
    znik
    -0.07
    cona
    -0.07
    uitka
    -0.07
    erli
    -0.07
    thal
    -0.07
     Caldwell
    -0.07
    oppable
    -0.07
    LastError
    -0.06
    POSITIVE LOGITS
    ÑĢож
    0.06
     Puerto
    0.06
     corpor
    0.06
    PU
    0.06
     McKay
    0.06
    alph
    0.06
     DbType
    0.06
    _misc
    0.05
     nerve
    0.05
    ÙĥÙĪر
    0.05
    Activations Density 0.001%

    No Known Activations