© 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. 9-LLAMASCOPE-RES-131K
    11. 98648
    Prev
    Next
    INDEX
    Explanations

    references to upcoming events or occurrences

    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
    abyrin
    -0.08
    /do
    -0.07
    oret
    -0.07
    riz
    -0.06
    zym
    -0.06
    orsch
    -0.06
    loquent
    -0.06
    abyrinth
    -0.06
    yll
    -0.06
    Ì
    -0.06
    POSITIVE LOGITS
    /current
    0.09
    /up
    0.08
    ĴĪ
    0.07
    etÃŃ
    0.07
    ç®Ĺ
    0.06
    ltra
    0.06
    datable
    0.06
    lÃŃ
    0.06
    /new
    0.06
    ÑĸÑĪ
    0.06
    Activations Density 0.006%

    No Known Activations