© 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. 38912
    Prev
    Next
    INDEX
    Explanations

    technical specifications and details related to electrical and USB connections

    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
    ubber
    -0.07
    .googleapis
    -0.07
    æķ
    -0.07
    Integration
    -0.07
    deaux
    -0.07
    ongan
    -0.06
     hé
    -0.06
    ttl
    -0.06
    prox
    -0.06
    haar
    -0.06
    POSITIVE LOGITS
    _adapter
    0.07
     polar
    0.07
    Charge
    0.07
    vos
    0.06
     Charge
    0.06
     Adapter
    0.06
    -pl
    0.06
    PILE
    0.06
    ingo
    0.06
     adapter
    0.06
    Activations Density 0.001%

    No Known Activations