© 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. 17-LLAMASCOPE-RES-131K
    11. 119041
    Prev
    Next
    INDEX
    Explanations

    programming and configuration-related keywords within project files

    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
    venth
    -0.08
    ksiyon
    -0.07
    multipart
    -0.07
    /topics
    -0.07
    cour
    -0.06
    ÄŁinden
    -0.06
    /span
    -0.06
    åĬ
    -0.06
    ÑĢаж
    -0.06
    IsNull
    -0.06
    POSITIVE LOGITS
     run
    0.09
    run
    0.07
     target
    0.06
    efore
    0.06
     profile
    0.06
    817
    0.06
     lint
    0.06
    orges
    0.06
    lint
    0.06
     combined
    0.06
    Activations Density 0.009%

    No Known Activations