© 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. 9-LLAMASCOPE-RES-131K
    11. 94837
    Prev
    Next
    INDEX
    Explanations

    numeric identifiers related to regulatory or project specifications

    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
    517
    -0.07
    inia
    -0.07
    oft
    -0.07
    combe
    -0.07
    plex
    -0.06
    lam
    -0.06
    ODB
    -0.06
    quette
    -0.06
    º
    -0.06
    848
    -0.06
    POSITIVE LOGITS
    /Gate
    0.07
    á»ĵng
    0.07
    ARGS
    0.06
    illis
    0.06
    idy
    0.06
    اÙģ
    0.06
     buflen
    0.06
    Å¡ak
    0.06
    ider
    0.06
    eter
    0.06
    Activations Density 0.093%

    No Known Activations