© 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. 120145
    Prev
    Next
    INDEX
    Explanations

    references to competitions and contests

    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
    rote
    -0.07
     Kauf
    -0.07
    adem
    -0.07
    æ¥
    -0.06
    ates
    -0.06
    iska
    -0.06
    isans
    -0.06
    pte
    -0.06
    tains
    -0.06
    grave
    -0.06
    POSITIVE LOGITS
    -winning
    0.10
    midd
    0.07
    terra
    0.07
    à¹ĥหà¸į
    0.07
    -lfs
    0.06
    mekte
    0.06
    jax
    0.06
    oeff
    0.06
    @js
    0.06
    æľŁéĸĵ
    0.06
    Activations Density 0.025%

    No Known Activations