© 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. 126650
    Prev
    Next
    INDEX
    Explanations

    text related to the history of significant events or movements

    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
    ìłł
    -0.07
    orm
    -0.07
    reta
    -0.06
     Heritage
    -0.06
    ienes
    -0.06
     umbrella
    -0.06
    ginas
    -0.06
    VEC
    -0.06
    undy
    -0.06
    Ùħز
    -0.06
    POSITIVE LOGITS
    ÑĥÑĢн
    0.07
     quot
    0.06
    Äħż
    0.06
     Proto
    0.06
     irresist
    0.06
    ury
    0.06
    å¼Ģ
    0.06
    ILED
    0.06
    mez
    0.06
     Escorts
    0.06
    Activations Density 0.113%

    No Known Activations