© 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. 2361
    Prev
    Next
    INDEX
    Explanations

    code structure elements such as functions, cases, and conditionals

    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
    ackets
    -0.08
    vanished
    -0.08
    Äįem
    -0.07
    /logging
    -0.07
    stad
    -0.07
    eç
    -0.07
    ائ
    -0.07
    phet
    -0.07
    roje
    -0.07
    loat
    -0.07
    POSITIVE LOGITS
    ulin
    0.06
     Bul
    0.06
     Tur
    0.06
    972
    0.05
     spell
    0.05
    nou
    0.05
    rena
    0.05
    oon
    0.05
     Magick
    0.05
     dev
    0.05
    Activations Density 0.199%

    No Known Activations