© 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. 54839
    Prev
    Next
    INDEX
    Explanations

    numerical values in the text

    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
    ifr
    -0.07
    Ú©Ø´
    -0.07
    addon
    -0.07
    inton
    -0.07
    iaux
    -0.07
    _COMPILE
    -0.06
    ipa
    -0.06
    mÄĽ
    -0.06
     Ñįлек
    -0.06
     Bren
    -0.06
    POSITIVE LOGITS
    otch
    0.06
    sci
    0.06
    roperty
    0.06
    Visitor
    0.06
     Williamson
    0.05
    iators
    0.05
    ##_
    0.05
    ĺ
    0.05
    &W
    0.05
    ETHOD
    0.05
    Activations Density 0.047%

    No Known Activations