© 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. 92295
    Prev
    Next
    INDEX
    Explanations

    discussions around fairness and equity

    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
    iná
    -0.08
    Äįe
    -0.07
    zin
    -0.07
    illet
    -0.07
    ç¸
    -0.07
    icari
    -0.07
    elho
    -0.06
    æĪ¸
    -0.06
    @testable
    -0.06
    lero
    -0.06
    POSITIVE LOGITS
     fairness
    0.08
     fair
    0.07
    ise
    0.07
     Fair
    0.07
    air
    0.07
     note
    0.06
    ific
    0.06
    ize
    0.06
    fair
    0.06
    istan
    0.06
    Activations Density 0.004%

    No Known Activations