© 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. 108442
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their usage in 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
    chia
    -0.09
    nable
    -0.09
    ULD
    -0.08
    OSE
    -0.07
    steder
    -0.07
    ADOW
    -0.07
     krev
    -0.07
    ruba
    -0.07
    ASF
    -0.07
    воÑĢ
    -0.07
    POSITIVE LOGITS
     mas
    0.06
    ecko
    0.06
     first
    0.06
    oller
    0.06
    ingroup
    0.06
    771
    0.06
     Stevenson
    0.06
     ent
    0.06
     res
    0.06
     prim
    0.06
    Activations Density 0.141%

    No Known Activations