© 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. 117666
    Prev
    Next
    INDEX
    Explanations

    specific punctuation marks and certain significant filler words in a document

    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
    mtree
    -0.06
    ocalypse
    -0.05
     Ø°
    -0.05
    елÑİ
    -0.05
     fra
    -0.05
    locking
    -0.05
    iver
    -0.05
    chter
    -0.05
     Midlands
    -0.05
     locked
    -0.05
    POSITIVE LOGITS
    á»Ļc
    0.07
    olle
    0.07
    alen
    0.07
    rames
    0.06
    endi
    0.06
    æī
    0.06
     ìĿ¸êµ¬
    0.06
    olt
    0.06
    igner
    0.06
    ryan
    0.06
    Activations Density 0.031%

    No Known Activations