© 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. 78545
    Prev
    Next
    INDEX
    Explanations

    programming-related property setting 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
    udeau
    -0.09
    onto
    -0.07
     Pend
    -0.07
    uther
    -0.06
    kinson
    -0.06
    undan
    -0.06
    azzo
    -0.06
    ibi
    -0.06
    udas
    -0.06
    ç´ł
    -0.06
    POSITIVE LOGITS
    tle
    0.07
    ##_
    0.07
    upal
    0.06
    emiz
    0.06
    äºķ
    0.06
    StringEncoding
    0.06
    é¡ĺ
    0.06
    éĹ
    0.06
    ted
    0.06
    -------------</
    0.06
    Activations Density 0.001%

    No Known Activations