© 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. 15-LLAMASCOPE-RES-131K
    11. 104311
    Prev
    Next
    INDEX
    Explanations

    words related to educational qualifications and graduations

    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
    ajs
    -0.08
    ocs
    -0.08
    afort
    -0.07
    stag
    -0.07
    å¹ħ
    -0.07
    ayers
    -0.07
    readcr
    -0.07
    /gtest
    -0.07
    _deinit
    -0.07
    ault
    -0.06
    POSITIVE LOGITS
     of
    0.09
    opia
    0.07
    ÙIJب
    0.07
     Graz
    0.06
     Emer
    0.06
     Neg
    0.06
    784
    0.06
    167
    0.06
    et
    0.06
    ORY
    0.06
    Activations Density 0.004%

    No Known Activations