Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 119333
    Prev
    Next
    INDEX
    Explanations

    phrases indicating recovery or returning from setbacks

    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
    ixels
    -0.07
     Ekon
    -0.07
    _PRESS
    -0.07
    emoc
    -0.07
     âĨĶ
    -0.07
    ndo
    -0.07
    esel
    -0.07
    andles
    -0.07
    _UL
    -0.07
    ãĤ«ãĥ¼
    -0.06
    POSITIVE LOGITS
     Tart
    0.06
     initially
    0.06
     pert
    0.06
     Rooney
    0.06
     edge
    0.06
     edges
    0.06
    abis
    0.06
     lost
    0.06
     lower
    0.06
     overs
    0.06
    Activations Density 0.007%

    No Known Activations