© 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. 61901
    Prev
    Next
    INDEX
    Explanations

    adverbs that describe frequency or regularity

    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
    allis
    -0.08
    apid
    -0.07
    fts
    -0.06
    Ế
    -0.06
    ãĥ³ãĥĦ
    -0.06
    ekim
    -0.06
    inh
    -0.06
    ifen
    -0.06
    ลาà¸Ķ
    -0.06
    ieri
    -0.06
    POSITIVE LOGITS
    urgence
    0.06
     either
    0.06
     Lem
    0.06
    acha
    0.06
    ãĥĥãĥĹ
    0.06
    ESP
    0.06
     ë§İìĿ´
    0.06
     bý
    0.06
    GRE
    0.06
    either
    0.06
    Activations Density 0.037%

    No Known Activations