© 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. 120657
    Prev
    Next
    INDEX
    Explanations

    attributes related to creativity and uniqueness

    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
    letes
    -0.07
    mans
    -0.07
    aret
    -0.07
    anela
    -0.07
    agger
    -0.07
    anking
    -0.06
    alsy
    -0.06
    langs
    -0.06
    zÃŃ
    -0.06
     bill
    -0.06
    POSITIVE LOGITS
     EITHER
    0.07
     EXEMPLARY
    0.06
    xffffff
    0.06
    ÑĤÑİ
    0.06
    باÙĨ
    0.06
     Revel
    0.06
     evid
    0.06
    ,eg
    0.06
    marsh
    0.06
    EGIN
    0.06
    Activations Density 0.000%

    No Known Activations