© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 78635
    Prev
    Next
    INDEX
    Explanations

    references to apprenticeships and workforce development programs

    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
    >window
    -0.07
    Teams
    -0.07
    Doctrine
    -0.07
    antt
    -0.07
    INU
    -0.07
    erken
    -0.07
     MatSnackBar
    -0.06
    irit
    -0.06
     gag
    -0.06
    Grey
    -0.06
    POSITIVE LOGITS
     Voc
    0.09
     employer
    0.09
     employers
    0.09
     Training
    0.09
     training
    0.08
     vocational
    0.08
     Employ
    0.08
     Industrial
    0.08
     Employer
    0.07
     acomp
    0.07
    Activations Density 0.049%

    No Known Activations