© 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. 94849
    Prev
    Next
    INDEX
    Explanations

    words related to practice and practitioners in various fields

    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
    ffective
    -0.08
    ieten
    -0.08
     вдÑĢÑĥг
    -0.07
    eric
    -0.07
    اÙĨÙĩ
    -0.07
    braco
    -0.07
    ulace
    -0.07
    &view
    -0.07
    olumn
    -0.07
     Newport
    -0.07
    POSITIVE LOGITS
    apos
    0.08
    ad
    0.07
    uk
    0.07
    jal
    0.06
    amp
    0.06
     perfect
    0.06
    ying
    0.06
    lin
    0.06
    ate
    0.06
    land
    0.06
    Activations Density 0.007%

    No Known Activations