© 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. 17-LLAMASCOPE-RES-131K
    11. 41208
    Prev
    Next
    INDEX
    Explanations

    terminology related to 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
    /he
    -0.07
    ustin
    -0.07
     Fortress
    -0.06
    ãĥ£
    -0.06
    mailer
    -0.06
    .Unicode
    -0.06
     Lust
    -0.06
    ondere
    -0.06
    unker
    -0.06
    :async
    -0.06
    POSITIVE LOGITS
    ments
    0.09
    ment
    0.09
    bole
    0.08
    LEM
    0.07
    ites
    0.07
    cript
    0.07
    able
    0.07
    ables
    0.07
    uche
    0.06
     hart
    0.06
    Activations Density 0.019%

    No Known Activations