© 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. 57336
    Prev
    Next
    INDEX
    Explanations

    punctuation-related elements 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
    ÑĥÑģÑĤа
    -0.07
    ãģ°ãģĭãĤĬ
    -0.06
     ruk
    -0.06
    .Transactional
    -0.06
     Zust
    -0.06
    _mv
    -0.06
    tml
    -0.06
    ¶Į
    -0.06
    "<?
    -0.06
    asc
    -0.06
    POSITIVE LOGITS
    entar
    0.07
    261
    0.07
    æ³³
    0.07
    idan
    0.06
    ATOR
    0.06
     erw
    0.06
     eag
    0.06
    ëļ
    0.06
    itet
    0.06
    <pre
    0.06
    Activations Density 0.011%

    No Known Activations