© 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. 9-LLAMASCOPE-RES-131K
    11. 96541
    Prev
    Next
    INDEX
    Explanations

    mentions of oppositions, contrasts, or dualities

    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
    ottes
    -0.08
    usercontent
    -0.08
    ibo
    -0.08
    UPPORTED
    -0.07
    ']!='
    -0.07
    екÑģ
    -0.07
    maz
    -0.07
    rame
    -0.07
    sets
    -0.07
    owell
    -0.07
    POSITIVE LOGITS
    -sex
    0.07
    adele
    0.07
    antly
    0.07
    ech
    0.07
    -minded
    0.06
     کاÙħÙĦ
    0.06
    -handed
    0.06
    /op
    0.06
    /all
    0.06
    ively
    0.06
    Activations Density 0.009%

    No Known Activations