© 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. 121123
    Prev
    Next
    INDEX
    Explanations

    references to recipes and cooking techniques

    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
    ude
    -0.08
    ach
    -0.07
    cher
    -0.07
    ma
    -0.07
    mal
    -0.07
    angers
    -0.07
    /ne
    -0.06
    mark
    -0.06
    reo
    -0.06
    ager
    -0.06
    POSITIVE LOGITS
    ulfilled
    0.08
    ofire
    0.08
    loff
    0.08
     dÄ±ÅŁÄ±
    0.07
    atron
    0.07
    çīĮ
    0.07
    anford
    0.07
    afort
    0.07
    books
    0.07
    bbie
    0.07
    Activations Density 0.005%

    No Known Activations