© 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. 85907
    Prev
    Next
    INDEX
    Explanations

    phrases indicating change or developments over time

    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
    ÑĮÑĤе
    -0.07
    pite
    -0.07
     exact
    -0.06
    exact
    -0.06
    ecute
    -0.06
    ä¸ĸ
    -0.06
    _exact
    -0.06
    ìĤ¬ë¬´
    -0.06
    alon
    -0.06
    ampie
    -0.06
    POSITIVE LOGITS
    aux
    0.09
    Ñĩи
    0.08
    anners
    0.07
    æ¢
    0.07
    elper
    0.07
     QLatin
    0.06
     happens
    0.06
     happen
    0.06
     NC
    0.06
     Zd
    0.06
    Activations Density 0.003%

    No Known Activations