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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 76257
    Prev
    Next
    INDEX
    Explanations

    references to job dissatisfaction and its impact on employees

    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
    inton
    -0.07
    uib
    -0.07
    gis
    -0.07
    doch
    -0.07
    asz
    -0.07
    oble
    -0.07
    ellig
    -0.07
    /gpl
    -0.07
    VT
    -0.06
    icum
    -0.06
    POSITIVE LOGITS
     among
    0.08
     key
    0.07
     major
    0.07
     the
    0.07
     Among
    0.06
     one
    0.06
    111
    0.06
    avage
    0.06
     primary
    0.06
     central
    0.06
    Activations Density 0.035%

    No Known Activations