© 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. 9-LLAMASCOPE-RES-131K
    11. 98154
    Prev
    Next
    INDEX
    Explanations

    punctuation and conjunctions that may indicate structure in writing

    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
    WithURL
    -0.07
    ÅĻev
    -0.07
    á»ģn
    -0.07
     hâl
    -0.06
     sorts
    -0.06
    ARGER
    -0.06
     seper
    -0.06
    075
    -0.06
    WebResponse
    -0.06
     Katz
    -0.06
    POSITIVE LOGITS
    enticated
    0.06
    idd
    0.06
     ret
    0.06
     ActionTypes
    0.06
    ylim
    0.06
    azon
    0.06
    oston
    0.06
    ergy
    0.06
    abase
    0.06
    efon
    0.06
    Activations Density 0.024%

    No Known Activations