© 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. 60659
    Prev
    Next
    INDEX
    Explanations

    questions or uncertainties about knowledge and experiences

    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
    emem
    -0.07
    /arch
    -0.07
    ãĤ¼
    -0.07
    ÙĮ
    -0.07
    emez
    -0.07
    emouth
    -0.06
    jsonp
    -0.06
    Sharper
    -0.06
    екÑģи
    -0.06
    issant
    -0.06
    POSITIVE LOGITS
     yet
    0.10
    yet
    0.09
     nor
    0.08
     but
    0.07
    -Smith
    0.07
     anymore
    0.06
    Yet
    0.06
    arters
    0.06
    ilar
    0.06
     hostage
    0.06
    Activations Density 0.031%

    No Known Activations