© 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. 57342
    Prev
    Next
    INDEX
    Explanations

    expressions related to being underestimated or written off

    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
    .scalablytyped
    -0.08
    ulace
    -0.07
    ande
    -0.07
    èŃ·
    -0.07
    UBY
    -0.07
    à¸Ļà¸Ķ
    -0.07
     PUS
    -0.07
    eof
    -0.07
    ammen
    -0.07
    âķĿ
    -0.07
    POSITIVE LOGITS
     preseason
    0.07
     predictions
    0.07
    media
    0.07
     pundits
    0.06
     pre
    0.06
     medi
    0.06
     predicted
    0.06
    hx
    0.06
    626
    0.06
    Coverage
    0.06
    Activations Density 0.033%

    No Known Activations