© 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. 121183
    Prev
    Next
    INDEX
    Explanations

    references to utility functions or methods

    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
    aven
    -0.07
    cho
    -0.07
    ymous
    -0.07
    .Accessible
    -0.07
    agen
    -0.07
    atab
    -0.07
    Fetching
    -0.07
    CHO
    -0.07
    ilet
    -0.06
    enco
    -0.06
    POSITIVE LOGITS
    634
    0.07
    ties
    0.07
    ies
    0.07
    iÅŁim
    0.07
    851
    0.07
    idades
    0.07
    vore
    0.07
     Belt
    0.07
    314
    0.06
    isateur
    0.06
    Activations Density 0.011%

    No Known Activations