© 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 EvalsExportsAPI 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. 87446
    Prev
    Next
    INDEX
    Explanations

    instances of numerical values and dates in the 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
    ıza
    -0.08
     poil
    -0.08
    iju
    -0.08
    Ư
    -0.08
    имо
    -0.07
    shaw
    -0.07
     LENG
    -0.07
    _________________↵↵
    -0.07
     baÅŁlan
    -0.07
    oux
    -0.07
    POSITIVE LOGITS
    TAG
    0.07
    463
    0.06
    825
    0.06
    DOI
    0.06
     tags
    0.05
     Fol
    0.05
     contested
    0.05
     fol
    0.05
    467
    0.05
    OO
    0.05
    Activations Density 0.039%

    No Known Activations