© 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. 59403
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "no" and related variations within citation 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
    esa
    -0.06
    oler
    -0.06
    ublisher
    -0.06
    abbix
    -0.06
    _FC
    -0.06
    esch
    -0.06
    ialog
    -0.06
    agina
    -0.06
    ikipedia
    -0.06
     наб
    -0.06
    POSITIVE LOGITS
    .issue
    0.07
    upa
    0.06
    ë§ŀ
    0.06
    ichten
    0.06
     iss
    0.06
     Mär
    0.06
    Ups
    0.06
     arrang
    0.06
    nave
    0.06
    upert
    0.06
    Activations Density 0.008%

    No Known Activations