© 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. 124952
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their frequency in the text

    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
    лин
    -0.07
    лÑĸн
    -0.07
    onas
    -0.07
    _Invoke
    -0.07
    .Marshal
    -0.06
    اØ
    -0.06
    é¢Ĩ
    -0.06
    ลล
    -0.06
     FAG
    -0.06
    .MixedReality
    -0.06
    POSITIVE LOGITS
     ÐľÑĸнÑĸÑģÑĤ
    0.07
    anyl
    0.06
    azu
    0.06
    arl
    0.06
     spectral
    0.06
    εÏĦ
    0.06
    arest
    0.06
    irt
    0.06
    ibel
    0.06
    PA
    0.06
    Activations Density 0.028%

    No Known Activations