© 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. 1821
    Prev
    Next
    INDEX
    Explanations

    terms related to community development and resources

    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
    инг
    -0.07
    instein
    -0.07
    .toolbox
    -0.07
    ping
    -0.06
     Kauf
    -0.06
    ân
    -0.06
     stranÄĽ
    -0.06
     inval
    -0.05
     Lesb
    -0.05
    Hardware
    -0.05
    POSITIVE LOGITS
     GmbH
    0.08
    âĢª
    0.07
    æľīéĻIJåħ¬åı¸
    0.07
    'gc
    0.07
    istringstream
    0.07
    mbH
    0.07
     Centre
    0.07
    &R
    0.07
    .firebaseapp
    0.07
     Pvt
    0.06
    Activations Density 0.070%

    No Known Activations