© 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. 16344
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly periods and commas

    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
    attempt
    -0.07
    gings
    -0.07
    βολ
    -0.07
    VERTISEMENT
    -0.07
    Attempt
    -0.06
    lendirme
    -0.06
    ÏĨεÏģ
    -0.06
    AGR
    -0.06
    uai
    -0.06
    à¹īาà¸ĩ
    -0.06
    POSITIVE LOGITS
     themselves
    0.07
     sayesinde
    0.07
     otherwise
    0.07
    -sama
    0.07
     even
    0.07
     resulting
    0.06
    avid
    0.06
    rof
    0.06
     pit
    0.06
     cul
    0.06
    Activations Density 0.048%

    No Known Activations