© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 1275
    Prev
    Next
    INDEX
    Explanations

    punctuation and formatting characters typically found in sequences or data strings

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    f
    -0.07
    851
    -0.07
    elho
    -0.07
    360
    -0.06
    513
    -0.06
    358
    -0.06
     confer
    -0.06
    *
    -0.06
     presum
    -0.06
    850
    -0.06
    POSITIVE LOGITS
    nech
    0.08
     nhau
    0.08
    [Byte
    0.07
    ,void
    0.07
    ?↵↵↵↵
    0.07
     Heller
    0.07
    оÑģ
    0.07
    istro
    0.07
    pector
    0.07
    _DX
    0.07
    Activations Density 0.001%

    No Known Activations