© 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. 16444
    Prev
    Next
    INDEX
    Explanations

    occurrences of parentheses or related formatting symbols

    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
     sip
    -0.07
    ox
    -0.06
     belg
    -0.06
    ods
    -0.06
    atı
    -0.06
    ส
    -0.06
    лова
    -0.06
    oe
    -0.06
    antz
    -0.06
    ÙħاÙħ
    -0.06
    POSITIVE LOGITS
    usercontent
    0.07
    ainers
    0.07
    ë¡ł
    0.07
     Williams
    0.06
    responseObject
    0.06
    pNet
    0.06
    ika
    0.06
    undler
    0.06
    ɵ
    0.06
    CEPT
    0.06
    Activations Density 0.005%

    No Known Activations