© 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. 29140
    Prev
    Next
    INDEX
    Explanations

    prefixes that indicate negation

    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
    folio
    -0.07
    çĮ®
    -0.07
    AZY
    -0.07
    åĩºæĿ¥
    -0.06
    ifax
    -0.06
    Äįet
    -0.06
    ادÛĮ
    -0.06
    ırak
    -0.06
    unsch
    -0.06
    letic
    -0.06
    POSITIVE LOGITS
    ãģ¡ãĤĩ
    0.07
    eton
    0.06
    ÃŃl
    0.06
    åĭ¤
    0.06
    (Of
    0.06
    iÃŃ
    0.06
    dden
    0.06
    /light
    0.06
    ieee
    0.06
    ̧
    0.06
    Activations Density 0.000%

    No Known Activations