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. 44361
    Prev
    Next
    INDEX
    Explanations

    references to historical figures or events related to resistance and oppression

    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
     nh
    -0.07
    Exposed
    -0.06
    ollah
    -0.06
     sheds
    -0.05
    shed
    -0.05
     shedding
    -0.05
    äch
    -0.05
    ØŃ
    -0.05
    ê
    -0.05
    uffman
    -0.05
    POSITIVE LOGITS
    Ä
    0.14
    Äįi
    0.14
     Åł
    0.14
     Už
    0.14
     Ž
    0.14
    .lt
    0.13
    ž
    0.13
    Å«
    0.13
     ž
    0.13
     ÄĮes
    0.12
    Activations Density 0.014%

    No Known Activations