© 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. 29314
    Prev
    Next
    INDEX
    Explanations

    instances of the word "opposed."

    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
    ston
    -0.07
    ish
    -0.07
    aze
    -0.06
    asil
    -0.06
    oba
    -0.06
    istics
    -0.06
     minim
    -0.06
    isha
    -0.06
    pra
    -0.06
    olt
    -0.06
    POSITIVE LOGITS
    piler
    0.08
    avad
    0.08
    ìĿ´íĦ°
    0.07
    sing
    0.07
    æĸ¼
    0.07
    avatel
    0.07
    grese
    0.07
    ħn
    0.07
    renom
    0.07
    s
    0.07
    Activations Density 0.003%

    No Known Activations