© 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. 15-LLAMASCOPE-RES-131K
    11. 88381
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases related to events and significant dates

    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
    åĿĤ
    -0.06
    essler
    -0.06
    ,nil
    -0.06
    956
    -0.06
    askell
    -0.05
    ia
    -0.05
    _tolerance
    -0.05
    år
    -0.05
    nil
    -0.05
    ilter
    -0.05
    POSITIVE LOGITS
    -Sah
    0.08
    enheim
    0.07
    ostel
    0.07
     Rencontre
    0.06
     dequeueReusableCellWithIdentifier
    0.06
    ÑĢеб
    0.06
    (íģ¬ê¸°
    0.06
    γά
    0.06
    DTD
    0.06
    иÑģÑĮ
    0.06
    Activations Density 0.023%

    No Known Activations