© 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 EvalsExportsAPI 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. 125750
    Prev
    Next
    INDEX
    Explanations

    technical terms and functions related to coding and data management

    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
     sag
    -0.07
     backing
    -0.06
     Sink
    -0.06
    Iterable
    -0.06
     Fab
    -0.06
     backed
    -0.06
     fined
    -0.06
    веÑĤ
    -0.06
    ç§ģãģ®
    -0.06
    éļ
    -0.06
    POSITIVE LOGITS
    -Origin
    0.07
    PEAR
    0.07
    smarty
    0.06
    ervoir
    0.06
    pollo
    0.06
    DM
    0.06
    pear
    0.06
    uniacid
    0.06
    serter
    0.06
    lesi
    0.06
    Activations Density 0.028%

    No Known Activations