© 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. 75096
    Prev
    Next
    INDEX
    Explanations

    references to job experiences and skills

    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
    917
    -0.08
    acon
    -0.07
    orate
    -0.07
    aub
    -0.07
    GIN
    -0.07
    aura
    -0.07
    oj
    -0.06
    upert
    -0.06
     Meanwhile
    -0.06
    folk
    -0.06
    POSITIVE LOGITS
     myself
    0.08
    лиÑĤелÑĮ
    0.07
     Blur
    0.07
     jsem
    0.07
     briefly
    0.06
     mostly
    0.06
    úc
    0.06
     mainly
    0.06
     my
    0.06
     minha
    0.06
    Activations Density 0.060%

    No Known Activations