© 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. 80009
    Prev
    Next
    INDEX
    Explanations

    phrases and words that symbolize concepts or ideas

    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
    .AutoScaleMode
    -0.09
    esser
    -0.08
    andbox
    -0.08
    Ùħز
    -0.08
    rane
    -0.07
    ervas
    -0.07
    amar
    -0.07
    _TYP
    -0.07
    esy
    -0.07
    egade
    -0.07
    POSITIVE LOGITS
    ically
    0.08
    symbol
    0.07
    ker
    0.07
     symbolic
    0.07
    -symbol
    0.06
     Symbol
    0.06
    ize
    0.06
     represent
    0.06
    .symbol
    0.06
    گر
    0.06
    Activations Density 0.010%

    No Known Activations