© 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. 28871
    Prev
    Next
    INDEX
    Explanations

    content related to cultural, historical, and technological themes

    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
    евеÑĢ
    -0.06
    IGIN
    -0.06
     ling
    -0.06
    coni
    -0.06
    angler
    -0.06
    iglia
    -0.06
    letic
    -0.06
    OTES
    -0.06
    isper
    -0.06
    pector
    -0.06
    POSITIVE LOGITS
    placeholders
    0.07
    uros
    0.07
     Incre
    0.07
    ez
    0.06
    sted
    0.06
    sville
    0.06
    /ay
    0.06
    天天
    0.06
    erton
    0.06
    seud
    0.06
    Activations Density 0.052%

    No Known Activations