© 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. 106347
    Prev
    Next
    INDEX
    Explanations

    phrases related to full-time employment and job roles

    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
     Dün
    -0.09
    oji
    -0.08
    ÑĦÑĦ
    -0.07
    kün
    -0.07
    Äł
    -0.07
    CHANT
    -0.07
    bane
    -0.07
    kat
    -0.07
    jang
    -0.07
    èľľ
    -0.07
    POSITIVE LOGITS
    /full
    0.11
    /part
    0.09
     permanent
    0.07
     equivalents
    0.07
     status
    0.07
    /temp
    0.06
     dedication
    0.06
     devoted
    0.06
     Partial
    0.06
    ers
    0.06
    Activations Density 0.005%

    No Known Activations