© 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. 29058
    Prev
    Next
    INDEX
    Explanations

    timestamps or temporal information

    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
     ust
    -0.08
    .cx
    -0.06
     strugg
    -0.06
    adata
    -0.06
     dumpster
    -0.06
    ìĹ°êµ¬
    -0.06
    è¾ŀ
    -0.06
    KA
    -0.06
    ades
    -0.06
    thouse
    -0.05
    POSITIVE LOGITS
    wik
    0.07
    spm
    0.07
     Fowler
    0.07
     Mvc
    0.07
    _mC
    0.07
    ucch
    0.07
    .updateDynamic
    0.07
    ucha
    0.07
    .mc
    0.07
    ãĥ»ãĥ»ãĥ»↵↵
    0.06
    Activations Density 0.002%

    No Known Activations