© 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. 42346
    Prev
    Next
    INDEX
    Explanations

    definitions and references related to programming interfaces and classes

    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
    rvé
    -0.08
    pline
    -0.07
    ά
    -0.07
     \`
    -0.07
    ebb
    -0.07
    alars
    -0.07
    LEM
    -0.07
    æīĭãĤĴ
    -0.06
     nedenle
    -0.06
    åĢij
    -0.06
    POSITIVE LOGITS
    ernes
    0.07
    iž
    0.07
    ảo
    0.07
    ï¸ı
    0.06
     Feld
    0.06
    нина
    0.06
    ropa
    0.06
    ellan
    0.06
    izens
    0.06
     Äijây
    0.05
    Activations Density 0.088%

    No Known Activations