© 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. 758
    Prev
    Next
    INDEX
    Explanations

    components of programming structure and logic related to functions and conditions

    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
    IPA
    -0.07
     Fle
    -0.06
    appa
    -0.06
    ระà¹Ģà¸ļ
    -0.05
     McCabe
    -0.05
     Randolph
    -0.05
    PÅĻÃŃ
    -0.05
    park
    -0.05
    printStats
    -0.05
     noses
    -0.05
    POSITIVE LOGITS
    brero
    0.07
     respondsToSelector
    0.07
     zbyt
    0.07
    maal
    0.07
    ắc
    0.07
    OST
    0.06
    OTAL
    0.06
     yoksa
    0.06
    zac
    0.06
    -webpack
    0.06
    Activations Density 0.137%

    No Known Activations