© 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. 72326
    Prev
    Next
    INDEX
    Explanations

    negative symbols or indicators related to performance

    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
    conde
    -0.09
    forman
    -0.07
    ÄįÃŃ
    -0.07
    elib
    -0.07
    $MESS
    -0.07
    ltra
    -0.07
    mdb
    -0.07
    Ìģt
    -0.07
    _marshall
    -0.07
    ılıp
    -0.07
    POSITIVE LOGITS
    [email
    0.06
     à¹Ĩ
    0.06
    ishi
    0.06
    Ĺ
    0.06
    anooga
    0.06
    ÑĥÑĪ
    0.06
     ingen
    0.06
    icha
    0.06
     seedu
    0.06
    elen
    0.05
    Activations Density 0.005%

    No Known Activations