© 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 EvalsExportsinterp-engineNEWAPI 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. 1654
    Prev
    Next
    INDEX
    Explanations

    expressions of personal preferences or dislikes

    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
     hopefully
    -0.07
    aux
    -0.06
    uter
    -0.06
    /event
    -0.06
    bau
    -0.06
    XB
    -0.06
    nego
    -0.06
    483
    -0.06
    ÃŁen
    -0.05
    çĢ
    -0.05
    POSITIVE LOGITS
     anymore
    0.13
     nor
    0.09
     necessarily
    0.08
    nor
    0.08
    奴
    0.07
    彦
    0.07
    à¹ĥà¸Ķ
    0.07
    ابات
    0.07
    Nor
    0.07
    .generated
    0.07
    Activations Density 0.009%

    No Known Activations