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. 5520
    Prev
    Next
    INDEX
    Explanations

    references to community engagement and cultural activities

    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
    iez
    -0.07
    íĹĮ
    -0.07
    ERM
    -0.07
    /error
    -0.07
    æĤ£
    -0.07
     flesh
    -0.06
    ibre
    -0.06
    idis
    -0.06
    íĮĮíĬ¸
    -0.06
    Leaks
    -0.06
    POSITIVE LOGITS
     youth
    0.11
     Youth
    0.09
     community
    0.09
     project
    0.09
     employ
    0.08
     social
    0.07
     regeneration
    0.07
     young
    0.07
     arts
    0.07
     gang
    0.07
    Activations Density 0.057%

    No Known Activations