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. 5628
    Prev
    Next
    INDEX
    Explanations

    emotional impacts and consequences related to tragic events

    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
    exus
    -0.07
    ileo
    -0.07
    =<?=$
    -0.07
    ÎŁÎ
    -0.07
    allis
    -0.07
    iversit
    -0.07
    sonian
    -0.07
    otify
    -0.07
    exas
    -0.07
    uced
    -0.07
    POSITIVE LOGITS
     comment
    0.06
     apprec
    0.06
     Replies
    0.06
    _o
    0.06
     comments
    0.06
     replies
    0.06
    æŃ³
    0.06
     COMMENTS
    0.06
    BT
    0.06
     Valent
    0.06
    Activations Density 0.019%

    No Known Activations