© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 77205
    Prev
    Next
    INDEX
    Explanations

    phrases indicating uncertainty or requests for clarification

    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
     FindObjectOfType
    -0.07
    .appspot
    -0.06
    wort
    -0.06
     GetComponent
    -0.06
    .tie
    -0.06
    ervo
    -0.06
    /board
    -0.06
     NSStringFromClass
    -0.06
     pard
    -0.06
    óa
    -0.06
    POSITIVE LOGITS
    Motion
    0.08
     Motion
    0.07
    Floor
    0.07
    motion
    0.07
    lider
    0.07
     motion
    0.06
     trav
    0.06
    gang
    0.06
    slick
    0.06
     Floor
    0.06
    Activations Density 0.003%

    No Known Activations