© 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. 28808
    Prev
    Next
    INDEX
    Explanations

    phrases indicating certainty or totality

    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
    ushima
    -0.07
    ylvania
    -0.07
    se
    -0.07
    rtle
    -0.06
    ombo
    -0.06
    egree
    -0.06
     Dash
    -0.06
    WEBPACK
    -0.06
    aland
    -0.06
    Dash
    -0.06
    POSITIVE LOGITS
    enger
    0.07
    oming
    0.07
     Nes
    0.06
    Cum
    0.06
    enes
    0.06
    еÑģп
    0.06
    òi
    0.06
    ë°Ķ
    0.06
     ÙģØ¥ÙĨ
    0.06
     esk
    0.06
    Activations Density 0.003%

    No Known Activations