© 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. 41604
    Prev
    Next
    INDEX
    Explanations

    numeric values and potential coordinates or identifiers

    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
    apon
    -0.08
    lide
    -0.07
    quit
    -0.07
    roat
    -0.07
    ictionaries
    -0.07
    ARSE
    -0.06
    bread
    -0.06
    é»
    -0.06
    aryawan
    -0.06
    lage
    -0.06
    POSITIVE LOGITS
    ways
    0.07
     ways
    0.06
    imagenes
    0.06
     Brooke
    0.06
    öy
    0.06
    amik
    0.06
     Elem
    0.06
    δÏģο
    0.05
    -legged
    0.05
    alion
    0.05
    Activations Density 0.078%

    No Known Activations