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. 44434
    Prev
    Next
    INDEX
    Explanations

    discussions related to HIV and its management

    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
    ìĩ
    -0.07
    allee
    -0.07
    ÙĦÙĬÙĩ
    -0.07
    ullan
    -0.07
    alle
    -0.07
    ↵↵
    -0.07
    جÙĩ
    -0.07
    .digital
    -0.07
    à¸Ĩ
    -0.06
    createUrl
    -0.06
    POSITIVE LOGITS
     PM
    0.12
     HIV
    0.12
     ART
    0.11
     Prevention
    0.10
     AR
    0.10
     AIDS
    0.10
     mother
    0.09
     MT
    0.09
     prevention
    0.09
     HTC
    0.09
    Activations Density 0.009%

    No Known Activations