© 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. 105070
    Prev
    Next
    INDEX
    Explanations

    references to the concept of immortality and related terms

    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
    dır
    -0.09
    eger
    -0.09
    emic
    -0.08
    çĸĹ
    -0.08
    çĽĸ
    -0.07
    =edge
    -0.07
    ĤŃ
    -0.07
    fur
    -0.07
    Ùģس
    -0.07
    lub
    -0.07
    POSITIVE LOGITS
    ized
    0.09
    izing
    0.08
    aires
    0.06
    ROADCAST
    0.06
    ously
    0.06
    amate
    0.06
    ize
    0.06
    ifer
    0.06
    ization
    0.06
     weekends
    0.06
    Activations Density 0.004%

    No Known Activations