© 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. 73707
    Prev
    Next
    INDEX
    Explanations

    punctuation and the use of commas in 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
    asm
    -0.07
     accept
    -0.06
    n
    -0.06
     Batch
    -0.06
    ih
    -0.06
    pig
    -0.06
     id
    -0.06
    ourcem
    -0.05
     imper
    -0.05
    2
    -0.05
    POSITIVE LOGITS
    #ab
    0.08
    姫
    0.08
    _TS
    0.08
    customize
    0.08
    견
    0.08
    ìĸ¼
    0.08
    disposed
    0.08
    egt
    0.07
    dealloc
    0.07
    Ñīин
    0.07
    Activations Density 0.008%

    No Known Activations