© 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. 108344
    Prev
    Next
    INDEX
    Explanations

    numerical values and their significance in various contexts

    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
     overnight
    -0.07
     Emp
    -0.07
    angl
    -0.06
    lifetime
    -0.06
    ünk
    -0.06
    tras
    -0.06
    çŀ¬
    -0.06
    Emp
    -0.06
     Sant
    -0.06
    indow
    -0.06
    POSITIVE LOGITS
    rien
    0.08
    uku
    0.08
    uten
    0.07
    loe
    0.07
    adt
    0.07
    èĨľ
    0.07
    окÑģи
    0.07
    RIX
    0.07
    .major
    0.07
    _prime
    0.07
    Activations Density 0.001%

    No Known Activations