© 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. 70081
    Prev
    Next
    INDEX
    Explanations

    descriptions of presentation effectiveness and adaptability

    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
     bound
    -0.06
    pard
    -0.06
    amburger
    -0.06
     server
    -0.06
     major
    -0.05
     daily
    -0.05
     massive
    -0.05
     Server
    -0.05
    urr
    -0.05
     G
    -0.05
    POSITIVE LOGITS
     visuals
    0.08
     Verfüg
    0.07
    linger
    0.07
     denom
    0.07
     ÙħÙĨاس
    0.07
    .LoggerFactory
    0.07
    ikip
    0.07
    /trunk
    0.07
     deja
    0.07
    urrenc
    0.07
    Activations Density 0.006%

    No Known Activations