© 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. 106967
    Prev
    Next
    INDEX
    Explanations

    instances of inheritance and superclass references in object-oriented programming 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
     Moines
    -0.07
    alo
    -0.07
     *__
    -0.06
    emi
    -0.06
    sid
    -0.06
    ema
    -0.06
     Bin
    -0.06
    nes
    -0.06
    alyzer
    -0.06
    mÃŃ
    -0.06
    POSITIVE LOGITS
    ordinate
    0.08
    iors
    0.07
    à¹Ĩ
    0.07
     à¹Ĩ
    0.07
    ordan
    0.07
    358
    0.07
    agina
    0.07
    ousel
    0.07
    538
    0.06
    ordinates
    0.06
    Activations Density 0.002%

    No Known Activations