© 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. 105129
    Prev
    Next
    INDEX
    Explanations

    punctuation marks that typically follow statements or declarative sentences

    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
    ilda
    -0.07
     tạm
    -0.07
     Wilkinson
    -0.07
    urrect
    -0.07
    imon
    -0.06
    ocale
    -0.06
    uno
    -0.06
     McD
    -0.06
    ieres
    -0.06
     hei
    -0.06
    POSITIVE LOGITS
     Feinstein
    0.08
    egin
    0.07
    usch
    0.07
    eper
    0.06
    borough
    0.06
    ugen
    0.06
    DisplayStyle
    0.06
    -runner
    0.06
    ovol
    0.06
    running
    0.06
    Activations Density 0.001%

    No Known Activations