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. 5490
    Prev
    Next
    INDEX
    Explanations

    instances of the word "when" in various contexts

    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
    apon
    -0.07
    rop
    -0.06
    ufen
    -0.06
    lio
    -0.06
    jing
    -0.06
    others
    -0.06
     others
    -0.06
    otte
    -0.06
     nawet
    -0.06
    eed
    -0.06
    POSITIVE LOGITS
     looking
    0.09
    ayette
    0.08
     talking
    0.07
    ÑĢиÑģÑĤи
    0.07
     correctly
    0.07
    eview
    0.07
    verity
    0.07
     properly
    0.07
    ÑģкоÑĢ
    0.07
     choosing
    0.07
    Activations Density 0.025%

    No Known Activations