© 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. 38895
    Prev
    Next
    INDEX
    Explanations

    expressions of large numerical values or counts

    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
    skip
    -0.07
    asso
    -0.07
    matic
    -0.07
    angel
    -0.07
    gin
    -0.07
    mie
    -0.07
    :///
    -0.07
    ative
    -0.07
     bdsm
    -0.06
    ayo
    -0.06
    POSITIVE LOGITS
    erva
    0.07
    agram
    0.07
    æĶ
    0.06
    undy
    0.06
    ln
    0.06
     SND
    0.05
     us
    0.05
    aires
    0.05
     Happy
    0.05
    reich
    0.05
    Activations Density 0.041%

    No Known Activations