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. 22-LLAMASCOPE-RES-131K
    6. 5599
    Prev
    Next
    INDEX
    Explanations

    expressions of sympathy and support

    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
    372
    -0.06
    /system
    -0.06
    ober
    -0.06
    airo
    -0.06
    andr
    -0.06
    anova
    -0.06
    okrat
    -0.06
     (
    -0.06
    UnderTest
    -0.06
    customize
    -0.06
    POSITIVE LOGITS
     kepada
    0.07
     toward
    0.07
     ìĤ¬íķŃ
    0.07
     message
    0.07
    ãĥ¼ãĥĨ
    0.07
     towards
    0.07
    HeaderCode
    0.06
     messages
    0.06
     onto
    0.06
    ÑĢеж
    0.06
    Activations Density 0.007%

    No Known Activations