© 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. 55972
    Prev
    Next
    INDEX
    Explanations

    phrases or inquiries related to discovering information or seeking answers

    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
    adden
    -0.07
    izard
    -0.06
     Equivalent
    -0.06
     ÙħÙĤدÙħ
    -0.06
    ULE
    -0.06
    enticate
    -0.06
    556
    -0.06
    raud
    -0.06
     Gib
    -0.06
    inos
    -0.06
    POSITIVE LOGITS
     details
    0.08
    详æĥħ
    0.07
     how
    0.07
    MPI
    0.07
     learn
    0.07
     detail
    0.06
    à¹Ģà¸Ĺ
    0.06
     why
    0.06
    shm
    0.06
    æĽ´å¤ļ
    0.06
    Activations Density 0.015%

    No Known Activations