© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 76112
    Prev
    Next
    INDEX
    Explanations

    discussions about change and vulnerability in personal narratives related to public figures or events

    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
     Gerr
    -0.07
    868
    -0.07
     gl
    -0.07
     اÙĦÙħÙĤ
    -0.07
     Batch
    -0.07
    urers
    -0.06
     Families
    -0.06
    aba
    -0.06
    rys
    -0.06
    amik
    -0.06
    POSITIVE LOGITS
     him
    0.10
     onun
    0.09
     his
    0.08
     그를
    0.08
     career
    0.08
     biography
    0.07
    Career
    0.07
     Biography
    0.07
     chez
    0.07
     ê·¸ìĿĺ
    0.07
    Activations Density 0.079%

    No Known Activations