© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 56311
    Prev
    Next
    INDEX
    Explanations

    references to specific organizations and their roles

    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
    itus
    -0.07
    jsc
    -0.06
    Detach
    -0.06
     Pavel
    -0.06
    uffle
    -0.06
     format
    -0.06
    ãģª
    -0.06
     nos
    -0.06
     taped
    -0.06
    _fs
    -0.06
    POSITIVE LOGITS
     каÑĩеÑģÑĤве
    0.07
     ÑĩиÑģлÑĸ
    0.07
    .onView
    0.07
    åľ°ä¸ĭ
    0.07
     muschi
    0.06
     Cause
    0.06
    jobs
    0.06
    .Dropout
    0.06
     hÆ°á»Łng
    0.06
    اÙĦØ¥ÙĨجÙĦÙĬزÙĬØ©
    0.06
    Activations Density 0.054%

    No Known Activations