© 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. 120032
    Prev
    Next
    INDEX
    Explanations

    conjunctions and articles in the text

    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
    cesso
    -0.07
    upo
    -0.07
    elez
    -0.07
    ctor
    -0.06
    amer
    -0.06
    sel
    -0.06
    cher
    -0.06
     cref
    -0.06
    ugging
    -0.06
    Ñijм
    -0.06
    POSITIVE LOGITS
    rew
    0.08
     ilk
    0.08
    REW
    0.07
    /of
    0.07
    /as
    0.07
    amp
    0.07
    raquo
    0.07
    REA
    0.07
     Others
    0.07
    rea
    0.06
    Activations Density 0.020%

    No Known Activations