© 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. 57368
    Prev
    Next
    INDEX
    Explanations

    instances of direct speech attributed to characters

    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
    ÄIJT
    -0.08
    elik
    -0.08
    женÑĮ
    -0.07
    urum
    -0.07
    SPATH
    -0.07
    ystack
    -0.07
    ħ
    -0.07
     addCriterion
    -0.07
    зано
    -0.07
    zel
    -0.07
    POSITIVE LOGITS
     cool
    0.05
     “
    0.05
    390
    0.05
     DataView
    0.05
     iron
    0.05
    /tcp
    0.05
    Ī
    0.05
    ,
    0.05
     dich
    0.05
    ivariate
    0.05
    Activations Density 0.011%

    No Known Activations