© 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 EvalsExportsinterp-engineNEWAPI 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. 77735
    Prev
    Next
    INDEX
    Explanations

    terms related to educational equity and the experiences of marginalized students

    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
     &
    -0.07
    hai
    -0.06
    PHA
    -0.06
    âĢ¦
    -0.06
     —
    -0.06
     -
    -0.06
    ystal
    -0.06
     [âĢ¦]↵
    -0.05
     [âĢ¦]
    -0.05
     "
    -0.05
    POSITIVE LOGITS
    podob
    0.09
    važ
    0.09
    ingers
    0.08
    etcode
    0.08
    plevel
    0.08
    üven
    0.08
    ูร
    0.07
    ίνα
    0.07
    .CG
    0.07
    HeaderCode
    0.07
    Activations Density 0.003%

    No Known Activations