© 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. 119698
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and other elements that indicate structural components in writing

    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
    ÑĨев
    -0.06
    ãĥ¬ãĤ¤
    -0.06
     Lust
    -0.06
    _READONLY
    -0.06
     mú
    -0.06
     Zu
    -0.06
    istrovstvÃŃ
    -0.06
    ç´Ģ
    -0.06
    ixer
    -0.06
     éħ
    -0.06
    POSITIVE LOGITS
    ANNEL
    0.08
    eteria
    0.07
    owell
    0.07
    nal
    0.07
    adows
    0.06
    ificados
    0.06
     Sweep
    0.06
    าà¸Ļ
    0.06
     célib
    0.06
    iyel
    0.06
    Activations Density 0.000%

    No Known Activations