© 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. 125790
    Prev
    Next
    INDEX
    Explanations

    statements expressing opinions or reasons about technology or consumer products

    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
     ведÑĮ
    -0.06
     just
    -0.06
     rest
    -0.06
     Gam
    -0.06
     means
    -0.06
    eg
    -0.06
     if
    -0.05
    imen
    -0.05
     enough
    -0.05
     Phil
    -0.05
    POSITIVE LOGITS
    å¦ĤæѤ
    0.08
     못
    0.08
    emann
    0.07
    ADM
    0.07
    ëĵł
    0.07
    emens
    0.07
    455
    0.07
     réuss
    0.07
    UILTIN
    0.07
     dolayı
    0.07
    Activations Density 0.013%

    No Known Activations