© 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. 116844
    Prev
    Next
    INDEX
    Explanations

    references to local industries and community issues

    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
    edo
    -0.07
     Freak
    -0.07
    bsd
    -0.07
    eba
    -0.07
    ^.
    -0.07
    xito
    -0.07
    ollah
    -0.07
    tte
    -0.06
    regist
    -0.06
     Westbrook
    -0.06
    POSITIVE LOGITS
     Job
    0.10
     Industry
    0.09
     industrial
    0.09
     industries
    0.09
     industry
    0.09
     job
    0.09
     jobs
    0.09
     employment
    0.08
     Employment
    0.08
     coal
    0.08
    Activations Density 0.010%

    No Known Activations