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. 11451
    Prev
    Next
    INDEX
    Explanations

    phrases indicating receiving or obtaining something

    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
     hold
    -0.07
    hold
    -0.07
    ertino
    -0.07
    polator
    -0.07
    ANGLES
    -0.06
    à¤Ĭ
    -0.06
    .wik
    -0.06
    ذ
    -0.06
     odst
    -0.06
    elts
    -0.06
    POSITIVE LOGITS
     asked
    0.12
     compliments
    0.10
     calls
    0.10
     requests
    0.10
     criticized
    0.10
     questioned
    0.09
     compliment
    0.09
     emails
    0.09
     approached
    0.09
     criticised
    0.08
    Activations Density 0.039%

    No Known Activations