© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 71832
    Prev
    Next
    INDEX
    Explanations

    occurrences of the phrase "of" in various 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
    à¸Ńà¸ĩà¸Īาà¸ģ
    -0.08
    áp
    -0.07
    _Abstract
    -0.07
    chooser
    -0.06
    .jav
    -0.06
    zburg
    -0.06
    berra
    -0.06
    udget
    -0.06
    ledge
    -0.06
    ullet
    -0.06
    POSITIVE LOGITS
    lander
    0.07
     this
    0.07
     main
    0.07
     tac
    0.06
     ass
    0.06
    ihad
    0.06
     unf
    0.06
     reason
    0.06
     born
    0.06
     oblig
    0.06
    Activations Density 0.010%

    No Known Activations