© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 98898
    Prev
    Next
    INDEX
    Explanations

    code structure and formatting elements in programming syntax

    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
    ÅĽnie
    -0.07
    lasses
    -0.06
    getic
    -0.06
    kt
    -0.06
    villa
    -0.06
    entrant
    -0.06
    urrect
    -0.06
    ideon
    -0.06
    CISION
    -0.06
    ughter
    -0.06
    POSITIVE LOGITS
    ERO
    0.07
     "?"
    0.06
     åľ
    0.06
     provid
    0.06
     доÑĢог
    0.06
    _GC
    0.06
    Frameworks
    0.06
     UIWindow
    0.06
    nas
    0.06
    erb
    0.06
    Activations Density 0.002%

    No Known Activations