© 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. 94116
    Prev
    Next
    INDEX
    Explanations

    inquiries about personal beliefs and opinions

    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
    ForResource
    -0.06
    _warnings
    -0.06
    ymm
    -0.06
    oh
    -0.06
    ByKey
    -0.06
    -Core
    -0.06
    ắng
    -0.06
     Thornton
    -0.06
    228
    -0.05
    587
    -0.05
    POSITIVE LOGITS
    еви
    0.07
    rait
    0.07
    igham
    0.06
    illez
    0.06
    errick
    0.06
    amura
    0.06
    à¤ł
    0.06
    evi
    0.06
    agli
    0.06
    LÄ°
    0.06
    Activations Density 0.006%

    No Known Activations