© 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. 107544
    Prev
    Next
    INDEX
    Explanations

    mentions of reports and studies related to consumer behavior and market trends

    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
     wes
    -0.06
    ocket
    -0.05
    chai
    -0.05
     Bol
    -0.05
    lein
    -0.05
    737
    -0.05
    295
    -0.05
    iminal
    -0.05
     kø
    -0.05
     bol
    -0.05
    POSITIVE LOGITS
     trend
    0.09
     Trend
    0.09
    rapy
    0.07
    /drivers
    0.07
    .Meta
    0.07
     createAction
    0.07
     posted
    0.07
    ponge
    0.06
     monthly
    0.06
    imo
    0.06
    Activations Density 0.007%

    No Known Activations