© 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 EvalsExportsAPI 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. 89036
    Prev
    Next
    INDEX
    Explanations

    various forms of punctuation marks

    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
    ĨĴ
    -0.07
    άÏĥ
    -0.06
     eventual
    -0.06
    hung
    -0.06
    enha
    -0.06
     Giz
    -0.06
     Lux
    -0.06
    oeff
    -0.06
    steller
    -0.06
    asco
    -0.06
    POSITIVE LOGITS
    unta
    0.07
    ough
    0.07
    atak
    0.07
     seedu
    0.07
    ught
    0.06
    okia
    0.06
    NDER
    0.06
    issan
    0.06
    omens
    0.06
    ensa
    0.06
    Activations Density 0.004%

    No Known Activations