© 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 EvalsExportsAPI 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. 57289
    Prev
    Next
    INDEX
    Explanations

    references to the name "Dave"

    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
    loh
    -0.08
    æķ
    -0.07
    orners
    -0.07
    vanished
    -0.07
    ëĵĿ
    -0.07
    ίθ
    -0.07
     kraje
    -0.07
    isper
    -0.07
    elts
    -0.07
    Ñģион
    -0.07
    POSITIVE LOGITS
    y
    0.12
    igh
    0.07
     Patch
    0.06
    onium
    0.06
    िड
    0.06
    yb
    0.06
    ذا
    0.06
     beaut
    0.06
    IGH
    0.05
    works
    0.05
    Activations Density 0.004%

    No Known Activations