© 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. 77281
    Prev
    Next
    INDEX
    Explanations

    boolean values and status indications in programming contexts

    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
    ulo
    -0.09
    inz
    -0.07
    -0.06
    orde
    -0.06
     Ing
    -0.06
    emo
    -0.06
     Herr
    -0.06
    omba
    -0.06
    ÙħÙĩ
    -0.06
     =
    -0.05
    POSITIVE LOGITS
    .PerformLayout
    0.09
    owitz
    0.09
    ategory
    0.07
    avid
    0.07
    dbuf
    0.07
    αιδ
    0.07
     ELSE
    0.06
    iginal
    0.06
     anale
    0.06
    ampp
    0.06
    Activations Density 0.017%

    No Known Activations