© 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. 128761
    Prev
    Next
    INDEX
    Explanations

    references to job markets and career prospects for university graduates

    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
    osy
    -0.06
    oya
    -0.06
     Sham
    -0.06
    SAFE
    -0.06
    Ìģ
    -0.06
    os
    -0.06
    èį
    -0.06
    éħį
    -0.06
    ucci
    -0.06
    osu
    -0.06
    POSITIVE LOGITS
    ":[{↵
    0.07
    /theme
    0.07
    /plugin
    0.07
     Median
    0.07
    -utils
    0.07
    jom
    0.07
     VARIANT
    0.07
    conde
    0.07
    generic
    0.07
    ë¥
    0.07
    Activations Density 0.010%

    No Known Activations