© 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 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. 126644
    Prev
    Next
    INDEX
    Explanations

    elements and components related to electrical wiring and switches

    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
    abee
    -0.07
    aben
    -0.07
    aza
    -0.07
    plorer
    -0.07
    ogi
    -0.07
    avana
    -0.06
    oglob
    -0.06
     Double
    -0.06
    olson
    -0.06
     McDon
    -0.06
    POSITIVE LOGITS
    èŀº
    0.06
    wand
    0.06
     Wand
    0.06
    _snd
    0.06
     green
    0.06
     Pend
    0.06
    ritz
    0.06
     há»ĵi
    0.06
     Cunning
    0.06
    PILE
    0.06
    Activations Density 0.003%

    No Known Activations