© 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. 79944
    Prev
    Next
    INDEX
    Explanations

    references to official appointments and nominations

    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
    ÑĥÑĢн
    -0.07
    iere
    -0.07
    ozo
    -0.06
    ily
    -0.06
     Zwe
    -0.06
    izza
    -0.06
    razier
    -0.06
    лоÑģÑı
    -0.06
    UILD
    -0.06
     Constit
    -0.06
    POSITIVE LOGITS
     Gum
    0.07
    426
    0.06
    Collapsed
    0.06
     jadx
    0.06
    авиÑģ
    0.06
    ittle
    0.06
    Exited
    0.06
    dling
    0.06
    ÃĹ↵↵
    0.06
    awner
    0.06
    Activations Density 0.008%

    No Known Activations