© 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. 72148
    Prev
    Next
    INDEX
    Explanations

    references to places of employment or work-related contexts

    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
     running
    -0.07
     cov
    -0.07
     yar
    -0.06
     negot
    -0.06
     cure
    -0.06
    enes
    -0.06
    гÑĥ
    -0.06
    inox
    -0.06
     interrog
    -0.06
     truy
    -0.06
    POSITIVE LOGITS
    984
    0.07
     Swe
    0.07
     Trot
    0.06
    uhan
    0.06
    .radioButton
    0.06
    ona
    0.06
    NR
    0.06
    sein
    0.06
     nackte
    0.06
    жд
    0.06
    Activations Density 0.000%

    No Known Activations