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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 61897
    Prev
    Next
    INDEX
    Explanations

    instances of decorators and routes within web framework code

    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
    tight
    -0.07
    nar
    -0.06
    icons
    -0.06
    paced
    -0.06
    ot
    -0.06
    ëħĦìĹIJ
    -0.06
    ONGL
    -0.06
     Rin
    -0.06
     Bas
    -0.06
     composition
    -0.06
    POSITIVE LOGITS
     addCriterion
    0.08
    uraa
    0.08
    ienes
    0.08
    isman
    0.08
    UsageId
    0.07
    unca
    0.07
     eskort
    0.07
     zdrav
    0.07
     escorte
    0.07
    SupportedContent
    0.07
    Activations Density 0.001%

    No Known Activations