© 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. 124959
    Prev
    Next
    INDEX
    Explanations

    measurements and distances in a technical context

    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
    ichel
    -0.07
    ocommerce
    -0.07
    ãĤīãģĽ
    -0.07
    -prepend
    -0.07
    éļ
    -0.06
    enheim
    -0.06
    iginal
    -0.06
    .spotify
    -0.06
    .pp
    -0.06
     AppModule
    -0.06
    POSITIVE LOGITS
     nearest
    0.09
     point
    0.07
     edge
    0.06
    nearest
    0.06
    ALLY
    0.06
    fur
    0.06
    far
    0.06
     Volk
    0.06
     Point
    0.06
     touching
    0.06
    Activations Density 0.029%

    No Known Activations