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. 43766
    Prev
    Next
    INDEX
    Explanations

    phrases related to community support and empowerment

    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
    ponce
    -0.08
    RICT
    -0.07
    rightness
    -0.07
    ietet
    -0.07
    itsu
    -0.07
    ằ
    -0.07
    icha
    -0.07
    ındır
    -0.07
    oteric
    -0.07
    adesh
    -0.06
    POSITIVE LOGITS
     healthy
    0.12
     safe
    0.11
     thriving
    0.10
     civ
    0.10
     economically
    0.10
     healthier
    0.10
     engaged
    0.10
     prosperous
    0.09
     connected
    0.09
     resilient
    0.09
    Activations Density 0.037%

    No Known Activations