© 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. 56193
    Prev
    Next
    INDEX
    Explanations

    concepts related to superhuman abilities and character strength

    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
    caffold
    -0.07
    orque
    -0.07
     republice
    -0.07
    atten
    -0.07
    uhan
    -0.07
    IRO
    -0.07
    ETO
    -0.07
    ç¿
    -0.06
    deÅŁ
    -0.06
    Mgr
    -0.06
    POSITIVE LOGITS
     eps
    0.06
     kill
    0.06
     abilities
    0.06
    holder
    0.06
    onet
    0.06
     kills
    0.06
     fight
    0.06
    -sidebar
    0.06
    ķĮ
    0.06
    oun
    0.05
    Activations Density 0.009%

    No Known Activations