© 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. 15-LLAMASCOPE-RES-131K
    11. 62272
    Prev
    Next
    INDEX
    Explanations

    references to influential figures and their characteristics or actions

    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
    "label
    -0.07
     antlr
    -0.06
    éĻIJ
    -0.06
    IDEO
    -0.06
    odyn
    -0.06
    oplan
    -0.06
    EntityType
    -0.06
    AtPath
    -0.06
     addCriterion
    -0.06
    ancel
    -0.06
    POSITIVE LOGITS
    leta
    0.06
    ewood
    0.06
    NG
    0.06
     chiff
    0.06
    661
    0.06
    905
    0.06
     اÙĦعاÙĦÙħÙĬØ©
    0.05
     consum
    0.05
    lify
    0.05
     Kurd
    0.05
    Activations Density 0.023%

    No Known Activations