© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 90119
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to performances or shows that capture attention

    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
    istrov
    -0.08
    İ
    -0.08
    629
    -0.07
    /fw
    -0.07
    unya
    -0.07
    ammer
    -0.07
    emes
    -0.07
    AR
    -0.07
    _drv
    -0.06
    [end
    -0.06
    POSITIVE LOGITS
    ague
    0.06
    ulaire
    0.06
     wed
    0.06
     reint
    0.06
    egl
    0.06
     whenever
    0.06
    MMdd
    0.06
    launcher
    0.06
     SAX
    0.06
    Interop
    0.06
    Activations Density 0.007%

    No Known Activations