© 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. 121192
    Prev
    Next
    INDEX
    Explanations

    PHP code snippets and syntax

    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
    ugen
    -0.07
    Ãłnh
    -0.07
    abel
    -0.07
    afen
    -0.07
    ÙĦÙĥ
    -0.06
    anzi
    -0.06
    atak
    -0.06
     Cir
    -0.06
    ABEL
    -0.06
    pellier
    -0.06
    POSITIVE LOGITS
    ÑĮе
    0.07
    taj
    0.07
     hind
    0.07
    XL
    0.06
    nesc
    0.06
     solemn
    0.06
    imuth
    0.06
    ÙĦسÙĦ
    0.06
     OTHERWISE
    0.06
     Arrays
    0.06
    Activations Density 0.012%

    No Known Activations