© 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. 29179
    Prev
    Next
    INDEX
    Explanations

    criteria and requirements related to nominations and eligibility

    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
    apa
    -0.07
    labs
    -0.06
    quil
    -0.06
    xl
    -0.06
    deprecated
    -0.06
     Circ
    -0.06
     Liberties
    -0.06
     Hull
    -0.06
    utz
    -0.06
    ĥģ
    -0.06
    POSITIVE LOGITS
    etri
    0.08
     legally
    0.07
     minimum
    0.07
    adle
    0.06
     either
    0.06
     EITHER
    0.06
     ì¦
    0.06
    è
    0.06
     legal
    0.06
     fairly
    0.06
    Activations Density 0.015%

    No Known Activations