© 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. 125977
    Prev
    Next
    INDEX
    Explanations

    acronyms and technical terms related to technology and medicine

    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
     energetic
    -0.07
    avors
    -0.07
    _keyboard
    -0.06
    ãĥŃãĥ¼
    -0.06
    rown
    -0.06
    ازات
    -0.06
     genç
    -0.06
    erville
    -0.06
    awah
    -0.06
    imet
    -0.06
    POSITIVE LOGITS
    aterangepicker
    0.06
    lander
    0.06
    itest
    0.06
    YD
    0.06
    //{{
    0.06
    ãĥ¼ãĥĦ
    0.06
    landers
    0.06
    yms
    0.06
    iš
    0.06
    virt
    0.06
    Activations Density 0.026%

    No Known Activations