© 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. 17-LLAMASCOPE-RES-131K
    11. 92966
    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
    -blind
    -0.08
    -scalable
    -0.07
    alytics
    -0.07
     ifndef
    -0.07
    uru
    -0.07
    ιÏĥ
    -0.07
    emin
    -0.07
    lock
    -0.07
    ungan
    -0.07
    Ñģем
    -0.07
    POSITIVE LOGITS
    º
    0.06
    oco
    0.06
     coli
    0.06
    ICO
    0.06
    yle
    0.05
    Ob
    0.05
     ramp
    0.05
    tep
    0.05
    lli
    0.05
    ATO
    0.05
    Activations Density 0.024%

    No Known Activations