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

    Neuronpedia

    Jacobian LensNEW
    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. 82865
    Prev
    Next
    INDEX
    Explanations

    references to different education levels

    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
    _gradients
    -0.07
    zel
    -0.06
    aticon
    -0.06
    ancel
    -0.06
    Dynamic
    -0.06
    aban
    -0.06
    laps
    -0.06
     veloc
    -0.06
    ropol
    -0.06
    airy
    -0.06
    POSITIVE LOGITS
    -level
    0.10
     level
    0.09
    /high
    0.07
    -sized
    0.07
    级
    0.07
    -Level
    0.07
    -aged
    0.06
    _Level
    0.06
    dre
    0.06
    EGA
    0.06
    Activations Density 0.006%

    No Known Activations