© 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. 15-LLAMASCOPE-RES-131K
    11. 90192
    Prev
    Next
    INDEX
    Explanations

    specific numerical data and references in a technical context

    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
    laus
    -0.07
    obel
    -0.07
        ↵    ↵
    -0.07
    TES
    -0.07
    lesc
    -0.07
    porn
    -0.07
    eer
    -0.07
    ovice
    -0.07
    onn
    -0.07
    arn
    -0.06
    POSITIVE LOGITS
    soever
    0.07
    fold
    0.07
    abouts
    0.07
    upiter
    0.07
    lsru
    0.06
    ãģ¿
    0.06
    criptor
    0.06
    andro
    0.06
    _attached
    0.06
    ä¸Ķ
    0.06
    Activations Density 0.077%

    No Known Activations