© 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. 54761
    Prev
    Next
    INDEX
    Explanations

    symbols and operators typically seen in programming or mathematical expressions

    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
    que
    -0.06
    lice
    -0.06
    arend
    -0.06
    pps
    -0.06
    501
    -0.06
    itoris
    -0.06
    294
    -0.05
     draw
    -0.05
     irresist
    -0.05
     threshold
    -0.05
    POSITIVE LOGITS
    zzle
    0.07
    .Localization
    0.07
    èĬĻ
    0.07
    .Abstractions
    0.07
    .WinForms
    0.07
    otation
    0.06
     Fucked
    0.06
     å¼µ
    0.06
    +='<
    0.06
    оÑİз
    0.06
    Activations Density 0.027%

    No Known Activations