Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 96228
    Prev
    Next
    INDEX
    Explanations

    instances of variable declarations and their assignments in 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
    edBy
    -0.08
    mey
    -0.08
    ovel
    -0.07
    اض
    -0.07
    agrams
    -0.07
     nues
    -0.07
    _zoom
    -0.07
     ÙĪØ±Ø²
    -0.07
    otec
    -0.07
     gratuiti
    -0.07
    POSITIVE LOGITS
     allo
    0.06
    äl
    0.06
    owski
    0.06
     s
    0.05
    itchen
    0.05
     Py
    0.05
     
    0.05
    EH
    0.05
    337
    0.05
    alli
    0.05
    Activations Density 0.014%

    No Known Activations