© 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. 5-LLAMASCOPE-RES-131K
    11. 125437
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, especially quotation marks

    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
    åİ»äºĨ
    -0.06
    rn
    -0.06
    ron
    -0.06
     Braun
    -0.06
    ash
    -0.06
     mp
    -0.06
    mn
    -0.06
    aka
    -0.06
    RN
    -0.06
    itm
    -0.06
    POSITIVE LOGITS
    olith
    0.08
    .EntityFramework
    0.07
    義
    0.07
    INLINE
    0.07
    çĽĬ
    0.07
     çľ
    0.07
    ibri
    0.07
    udeau
    0.07
     bindActionCreators
    0.07
     ð
    0.06
    Activations Density 0.018%

    No Known Activations