© 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. 71872
    Prev
    Next
    INDEX
    Explanations

    tokens that represent changes or transformations in various contexts

    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
    artz
    -0.07
    +</
    -0.07
    ĸ
    -0.07
    ¶Į
    -0.06
     Lent
    -0.06
    rien
    -0.06
     éĵģ
    -0.06
    acho
    -0.06
    reich
    -0.06
    loys
    -0.06
    POSITIVE LOGITS
    (equalTo
    0.06
    iyel
    0.06
     Colbert
    0.06
    VG
    0.06
    egt
    0.06
     дело
    0.06
    ìłIJ
    0.06
     onAnimation
    0.06
     Butterfly
    0.06
     tob
    0.05
    Activations Density 0.283%

    No Known Activations