© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 71411
    Prev
    Next
    INDEX
    Explanations

    details about travel itineraries and associated costs

    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
    à¥Įड
    -0.07
    Æ°á»Ľc
    -0.07
    ÑģÑĭл
    -0.07
    æ±Ĺ
    -0.06
    [__
    -0.06
    loor
    -0.06
    \Lib
    -0.06
    Ñģл
    -0.06
    oble
    -0.06
    íĩ´
    -0.06
    POSITIVE LOGITS
    ãĥ¼ãĤ¸
    0.07
    opis
    0.07
    hotel
    0.06
     tast
    0.06
     mon
    0.06
     hotel
    0.06
    uml
    0.06
    dbl
    0.06
    ellido
    0.06
    adil
    0.06
    Activations Density 0.015%

    No Known Activations