© 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. 107771
    Prev
    Next
    INDEX
    Explanations

    details related to project requirements and resume formatting

    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
    ghan
    -0.08
    oidal
    -0.07
     Fork
    -0.07
    edis
    -0.07
    ogan
    -0.07
     fork
    -0.06
    ater
    -0.06
    isma
    -0.06
     hopefully
    -0.06
     Rencontre
    -0.06
    POSITIVE LOGITS
    /tos
    0.07
    ãĥĮ
    0.07
    اÙħÙĩ
    0.07
     Fountain
    0.07
    .sponge
    0.07
    ÑĦик
    0.07
    fet
    0.06
    ापà¤ķ
    0.06
    ÃĸL
    0.06
    ord
    0.06
    Activations Density 0.006%

    No Known Activations