© 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. 74981
    Prev
    Next
    INDEX
    Explanations

    expressions of support and concern in discussions regarding policy and initiatives

    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
    lus
    -0.07
    bern
    -0.07
    eto
    -0.07
    ampie
    -0.06
    tin
    -0.06
    Äħd
    -0.06
    tas
    -0.06
    ÙħØ´
    -0.06
    thers
    -0.06
    dfa
    -0.06
    POSITIVE LOGITS
    едж
    0.06
    /goto
    0.06
    Ø·ÙĦ
    0.06
    onna
    0.06
    ycop
    0.06
    /stdc
    0.06
    407
    0.06
    çļĦæĺ¯
    0.06
     ÑģоÑģÑĤоÑı
    0.06
     actionBar
    0.06
    Activations Density 0.024%

    No Known Activations