© 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. 2272
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and symbols 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
    ystack
    -0.07
    unga
    -0.07
    ervas
    -0.07
    aat
    -0.06
    å¤
    -0.06
    uju
    -0.06
    isse
    -0.06
    eways
    -0.06
    uÃŃ
    -0.06
    yre
    -0.06
    POSITIVE LOGITS
     Pell
    0.07
    webdriver
    0.07
    ISTR
    0.06
    deo
    0.06
    OTTOM
    0.06
    ада
    0.05
    parentNode
    0.05
    edn
    0.05
    éIJĺ
    0.05
    æ°ij
    0.05
    Activations Density 0.000%

    No Known Activations