© 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. 77248
    Prev
    Next
    INDEX
    Explanations

    references to "Good" along with related content or themes

    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
    uhl
    -0.07
    opsis
    -0.07
     cult
    -0.06
    akan
    -0.06
    ylum
    -0.06
     Tib
    -0.06
    eros
    -0.06
    OPSIS
    -0.06
    laz
    -0.06
     Shib
    -0.06
    POSITIVE LOGITS
    reads
    0.09
    bye
    0.09
    win
    0.08
    ness
    0.07
    onya
    0.07
    виÑĩ
    0.07
    reau
    0.07
    phin
    0.07
     Sachs
    0.07
    hots
    0.07
    Activations Density 0.012%

    No Known Activations