© 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. 126604
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "the"

    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
    //{{
    -0.08
    ouro
    -0.07
    enberg
    -0.07
    rych
    -0.07
     поб
    -0.07
    пеÑĩ
    -0.07
    аблиÑĨ
    -0.07
    \Backend
    -0.07
    ÑĤие
    -0.07
    rien
    -0.06
    POSITIVE LOGITS
     meantime
    0.10
     midst
    0.09
     absence
    0.08
     wake
    0.08
     hopes
    0.08
     case
    0.07
     eyes
    0.07
    wake
    0.07
     middle
    0.07
     throws
    0.06
    Activations Density 0.326%

    No Known Activations