© 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. 56183
    Prev
    Next
    INDEX
    Explanations

    expressions that indicate a need for awareness or consideration of differences

    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
    llib
    -0.09
    /fw
    -0.08
    alette
    -0.08
    bai
    -0.07
    endcode
    -0.07
    @js
    -0.07
    HeaderCode
    -0.07
    urette
    -0.07
    ogh
    -0.07
    latent
    -0.07
    POSITIVE LOGITS
     even
    0.06
    anda
    0.06
    ongo
    0.06
     /*
    0.06
     whatever
    0.06
    --
    0.06
    /*
    0.06
     insign
    0.05
    \
    0.05
     perhaps
    0.05
    Activations Density 0.000%

    No Known Activations