© 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. 106603
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and syntax

    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
    aru
    -0.08
     sou
    -0.07
    oni
    -0.06
    ault
    -0.06
     volta
    -0.06
    ugg
    -0.06
    air
    -0.06
    hausen
    -0.06
    iegel
    -0.06
     Ten
    -0.06
    POSITIVE LOGITS
     é¤
    0.06
    gens
    0.06
    brtc
    0.06
    ModelProperty
    0.06
    ovit
    0.06
    ī
    0.06
    .python
    0.06
    faction
    0.06
    hen
    0.06
    cin
    0.06
    Activations Density 0.003%

    No Known Activations