© 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. 120484
    Prev
    Next
    INDEX
    Explanations

    references to specific product models and specifications in the context of technology or engineering

    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
    rale
    -0.08
    rai
    -0.07
    embr
    -0.06
    Âłin
    -0.06
    utenberg
    -0.06
    andel
    -0.06
    158
    -0.05
    unn
    -0.05
     rien
    -0.05
    swana
    -0.05
    POSITIVE LOGITS
    iyat
    0.09
    _lite
    0.09
     fitte
    0.08
    plusplus
    0.08
     ï¼į
    0.08
    #ab
    0.08
    Æ¡
    0.08
    ï¼Ĭ
    0.08
    .lex
    0.08
    imizer
    0.08
    Activations Density 0.056%

    No Known Activations