© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 16413
    Prev
    Next
    INDEX
    Explanations

    data related to HIV prevalence and statistics

    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
     Cly
    -0.07
    éĢīæĭ
    -0.07
    usercontent
    -0.07
    ERO
    -0.07
     Slug
    -0.07
     incel
    -0.07
     Sabb
    -0.06
     trot
    -0.06
    DISABLE
    -0.06
    ertz
    -0.06
    POSITIVE LOGITS
     HIV
    0.19
     AIDS
    0.17
    /AIDS
    0.12
     gay
    0.09
    gay
    0.07
     CD
    0.07
    IDS
    0.07
     stigma
    0.07
    poz
    0.07
     viral
    0.07
    Activations Density 0.036%

    No Known Activations