© 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. 15-LLAMASCOPE-RES-131K
    11. 505
    Prev
    Next
    INDEX
    Explanations

    instances of the word "in."

    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
    kate
    -0.07
     Tess
    -0.06
    ãģĵãģĨ
    -0.06
    ittel
    -0.06
     parch
    -0.06
    ÙĩÙĩ
    -0.06
    wives
    -0.06
    worm
    -0.06
    _cmp
    -0.06
    åŃĺäºİ
    -0.06
    POSITIVE LOGITS
    .TestCase
    0.06
    ê°IJ
    0.06
    ÑģÑĤÑĢо
    0.06
    atre
    0.06
    iot
    0.06
    mada
    0.06
    SEA
    0.06
    yan
    0.06
    icare
    0.06
    iram
    0.06
    Activations Density 0.002%

    No Known Activations