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

    Neuronpedia

    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. 70714
    Prev
    Next
    INDEX
    Explanations

    references to ownership or description in context

    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
    ataires
    -0.08
    /people
    -0.07
    enci
    -0.07
    ynes
    -0.07
    chw
    -0.07
    ạ
    -0.07
    á»ĵn
    -0.07
    _CID
    -0.07
    chet
    -0.07
    758
    -0.07
    POSITIVE LOGITS
     how
    0.14
     what
    0.10
    how
    0.09
     the
    0.09
     exactly
    0.08
     sorts
    0.08
     why
    0.07
     hoe
    0.07
     current
    0.07
     behalf
    0.07
    Activations Density 0.082%

    No Known Activations