© 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. 59243
    Prev
    Next
    INDEX
    Explanations

    statements or questions related to scientific comparisons and relationships

    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
     riff
    -0.06
    teil
    -0.06
    меÑī
    -0.06
    ikat
    -0.06
    Logic
    -0.06
    _logic
    -0.06
     springfox
    -0.06
     scheduling
    -0.06
     flo
    -0.06
    омина
    -0.06
    POSITIVE LOGITS
     Williamson
    0.07
     tent
    0.06
    æĹı
    0.06
    angan
    0.06
     pairwise
    0.06
    .matcher
    0.06
    inz
    0.06
    isiyle
    0.06
     PROCUREMENT
    0.06
    justify
    0.06
    Activations Density 0.001%

    No Known Activations