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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 31-LLAMASCOPE-RES-131K
    6. 44448
    Prev
    Next
    INDEX
    Explanations

    references to political events and government formation

    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
    ogy
    -0.08
    angstrom
    -0.07
     kang
    -0.07
    apus
    -0.07
     kus
    -0.06
     Manuals
    -0.06
    ltk
    -0.06
    سÙĨÚ¯
    -0.06
    SetColor
    -0.06
    hattan
    -0.06
    POSITIVE LOGITS
     RN
    0.12
     Stuff
    0.12
    RN
    0.12
    Stuff
    0.11
     stuff
    0.10
     Audio
    0.10
    stuff
    0.10
     audio
    0.10
     AUDIO
    0.09
     Radio
    0.09
    Activations Density 0.011%

    No Known Activations