© 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. 38798
    Prev
    Next
    INDEX
    Explanations

    repeated references to a series or structure 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
     Balance
    -0.07
     Nam
    -0.07
     balance
    -0.06
    _reporting
    -0.06
     hus
    -0.06
    eyer
    -0.06
     aged
    -0.06
    akash
    -0.06
    164
    -0.06
     opposite
    -0.06
    POSITIVE LOGITS
     series
    0.10
     serie
    0.08
     saga
    0.08
    .series
    0.08
    series
    0.08
    -series
    0.07
     SERIES
    0.07
     Series
    0.07
     Spells
    0.07
    multi
    0.07
    Activations Density 0.031%

    No Known Activations