© 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. 87492
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their distribution in sentences

    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
    amiliar
    -0.07
    argent
    -0.07
    ingles
    -0.06
    iangle
    -0.06
    ÙħÙĪد
    -0.06
    etest
    -0.06
    ilden
    -0.06
    mtree
    -0.06
    uars
    -0.06
    ÑĨенÑĤÑĢа
    -0.06
    POSITIVE LOGITS
    è§
    0.07
    Besides
    0.06
    Born
    0.06
     Born
    0.06
    AMB
    0.06
     Soda
    0.06
    c
    0.06
     Besides
    0.06
     besides
    0.05
    rary
    0.05
    Activations Density 0.012%

    No Known Activations