© 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. 129771
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and signs of code 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
    rlen
    -0.07
    bcc
    -0.07
    tron
    -0.07
    deaux
    -0.06
    aylor
    -0.06
    usk
    -0.06
    WithMany
    -0.06
    WithError
    -0.06
    ég
    -0.06
    epam
    -0.06
    POSITIVE LOGITS
     whole
    0.06
    orna
    0.06
    ãģ¾ãģ¾
    0.06
     Cros
    0.06
     Jill
    0.06
    endas
    0.06
    à¹Ģลย
    0.06
    ople
    0.06
     entire
    0.06
    eos
    0.06
    Activations Density 0.000%

    No Known Activations