© 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. 78417
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, specifically periods

    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
    isti
    -0.07
    aris
    -0.06
    asion
    -0.06
     NotSupportedException
    -0.06
    oter
    -0.06
    ay
    -0.06
     uns
    -0.06
    ukkan
    -0.06
     feasible
    -0.06
    ori
    -0.06
    POSITIVE LOGITS
     lạ
    0.07
    unan
    0.06
    بÙĪاسطة
    0.06
    íĥķ
    0.06
    LIKELY
    0.06
    acher
    0.06
    ilen
    0.06
    енÑĥ
    0.06
    ','#
    0.06
    _hdl
    0.06
    Activations Density 0.002%

    No Known Activations