© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 1455
    Prev
    Next
    INDEX
    Explanations

    job titles and professional roles within organizational 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
    938
    -0.06
     like
    -0.06
    ayas
    -0.06
     rather
    -0.06
     experiment
    -0.05
    emes
    -0.05
    pell
    -0.05
     h
    -0.05
     b
    -0.05
     host
    -0.05
    POSITIVE LOGITS
    roperties
    0.07
     Company
    0.07
    ÄĽr
    0.07
    webtoken
    0.07
     prostituer
    0.07
    Ãły
    0.07
    гал
    0.07
    ADX
    0.06
    ACKET
    0.06
    omen
    0.06
    Activations Density 0.014%

    No Known Activations