© 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. 105102
    Prev
    Next
    INDEX
    Explanations

    elements relevant to patient care and education

    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
    öy
    -0.07
    iram
    -0.07
    bdd
    -0.07
    iddi
    -0.07
    _isr
    -0.07
     Raphael
    -0.06
    QualifiedName
    -0.06
    ood
    -0.06
    ormal
    -0.06
     Jad
    -0.06
    POSITIVE LOGITS
     pre
    0.13
     prepar
    0.12
     prep
    0.12
     preparation
    0.11
     pré
    0.11
     Pre
    0.10
     Prep
    0.10
     preparations
    0.10
    pre
    0.10
     prepare
    0.10
    Activations Density 0.027%

    No Known Activations