© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 87016
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their frequencies 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
    ÑĪки
    -0.07
     باع
    -0.07
    foon
    -0.07
    lesen
    -0.07
    ÙĤÛĮ
    -0.07
    ifestyles
    -0.07
     Mein
    -0.06
    ней
    -0.06
    duk
    -0.06
    tings
    -0.06
    POSITIVE LOGITS
     «
    0.08
    946
    0.07
     “
    0.07
     ``
    0.07
    ãĢĮ
    0.07
     \"
    0.06
     "
    0.06
     ph
    0.06
    âĢ³
    0.06
     ÅŁÃ¶yle
    0.06
    Activations Density 0.009%

    No Known Activations