© 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. 90234
    Prev
    Next
    INDEX
    Explanations

    specific programming and software development terminology

    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
    >{!!
    -0.07
    veal
    -0.07
     Gig
    -0.06
    plets
    -0.06
    -hooks
    -0.06
     IonicModule
    -0.06
    ugg
    -0.06
    pcl
    -0.06
     til
    -0.06
    titleLabel
    -0.06
    POSITIVE LOGITS
     Tw
    0.08
    itage
    0.07
    ết
    0.07
    maz
    0.07
    ÛĮات
    0.07
    dash
    0.07
    εÏĢ
    0.07
    embros
    0.07
    olds
    0.07
    owitz
    0.06
    Activations Density 0.001%

    No Known Activations