© 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. 17383
    Prev
    Next
    INDEX
    Explanations

    technical specifications and categorizations in product descriptions

    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
    íħ
    -0.07
    éĵ
    -0.07
    .builders
    -0.07
    нож
    -0.07
     Frid
    -0.07
    ικοÏį
    -0.07
     >",
    -0.06
    Ĥ¹
    -0.06
    ,www
    -0.06
    hart
    -0.06
    POSITIVE LOGITS
    :
    0.14
     :
    0.08
    ï¼ļ
    0.08
    西çľģ
    0.07
    (s
    0.07
    :**
    0.06
    ätz
    0.06
    ĵåIJį
    0.06
    thed
    0.05
    ा:
    0.05
    Activations Density 0.073%

    No Known Activations