© 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. 120217
    Prev
    Next
    INDEX
    Explanations

    persistent expressions of availability or support

    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
    ugo
    -0.07
    erson
    -0.07
     Leone
    -0.06
    cz
    -0.06
     å·
    -0.06
     наÑģÑĤÑĥп
    -0.06
    kaar
    -0.06
    UCH
    -0.06
    ucht
    -0.06
    ton
    -0.06
    POSITIVE LOGITS
    703
    0.07
    .AutoSizeMode
    0.07
    uada
    0.07
    麻
    0.06
    akening
    0.06
    YST
    0.06
     Albert
    0.06
    ptest
    0.06
    .documentation
    0.06
    ض
    0.06
    Activations Density 0.007%

    No Known Activations