© 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. 83705
    Prev
    Next
    INDEX
    Explanations

    specific symbols and punctuation marks within 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
    umann
    -0.06
    oth
    -0.06
    radan
    -0.06
     Roch
    -0.06
    amm
    -0.06
    APPER
    -0.06
     Beaver
    -0.06
    dont
    -0.05
     pseudo
    -0.05
     Bieber
    -0.05
    POSITIVE LOGITS
    aca
    0.07
    LEY
    0.07
     MPU
    0.07
     Byl
    0.07
    unte
    0.07
    _hooks
    0.07
    clave
    0.07
     réuss
    0.07
    ilst
    0.07
    endale
    0.07
    Activations Density 0.002%

    No Known Activations