© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 85003
    Prev
    Next
    INDEX
    Explanations

    details about planned events or activities

    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
    殿
    -0.08
    apolis
    -0.07
    yk
    -0.07
     volley
    -0.06
     culture
    -0.06
    olin
    -0.06
    _contin
    -0.06
    anas
    -0.06
    auth
    -0.06
    lav
    -0.06
    POSITIVE LOGITS
     Garmin
    0.07
    isper
    0.07
    bbox
    0.07
    ispers
    0.07
    isy
    0.07
    .blog
    0.07
    chas
    0.06
    rane
    0.06
    çĬ¬
    0.06
     permit
    0.06
    Activations Density 0.019%

    No Known Activations