© 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. 61790
    Prev
    Next
    INDEX
    Explanations

    episode or issue numbers associated with discussions or content releases

    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
    abra
    -0.06
    ÙĤاÙĦ
    -0.06
    ary
    -0.06
     ç¯
    -0.05
    led
    -0.05
    EAR
    -0.05
    mit
    -0.05
     view
    -0.05
    око
    -0.05
     domain
    -0.05
    POSITIVE LOGITS
    .scalablytyped
    0.09
     MEDIATEK
    0.08
    iversit
    0.08
    ridge
    0.08
     omas
    0.07
    erdem
    0.07
     nuest
    0.07
    redients
    0.07
    HeaderCode
    0.07
    ì°°
    0.07
    Activations Density 0.019%

    No Known Activations