© 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. 94208
    Prev
    Next
    INDEX
    Explanations

    descriptions of experiences related to entering or exploring spaces

    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
    leen
    -0.06
    utm
    -0.06
    drawing
    -0.06
    esin
    -0.06
    ovsky
    -0.06
     nearby
    -0.06
    nova
    -0.06
    æº
    -0.06
     ripple
    -0.05
    å¹¹ç·ļ
    -0.05
    POSITIVE LOGITS
     Entered
    0.07
    urre
    0.07
    Entered
    0.07
     sudden
    0.07
     æ¬
    0.07
    ampo
    0.06
    onto
    0.06
    aeper
    0.06
    autorelease
    0.06
    untlet
    0.06
    Activations Density 0.021%

    No Known Activations