© 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. 30406
    Prev
    Next
    INDEX
    Explanations

    references to a specific organization or institution

    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
    zym
    -0.07
    adu
    -0.07
    isher
    -0.07
    xies
    -0.07
    suz
    -0.07
    seo
    -0.07
    zes
    -0.06
    ypad
    -0.06
    nim
    -0.06
     defaultCenter
    -0.06
    POSITIVE LOGITS
    keeping
    0.11
    guest
    0.10
    boat
    0.09
    wives
    0.09
    plants
    0.09
    wife
    0.08
    breaking
    0.08
    keeper
    0.08
    boats
    0.08
    irth
    0.07
    Activations Density 0.020%

    No Known Activations