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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 128225
    Prev
    Next
    INDEX
    Explanations

    topics related to smoking regulations and health impacts

    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
    piel
    -0.07
    nemonic
    -0.07
    arpa
    -0.06
    avar
    -0.06
    endon
    -0.06
    ìłĿ
    -0.06
    ÃŃd
    -0.06
    elow
    -0.06
    diag
    -0.06
    hend
    -0.06
    POSITIVE LOGITS
     smoking
    0.11
     Smoking
    0.10
     cigarette
    0.09
     tobacco
    0.09
     smoke
    0.09
     smokers
    0.08
     indoor
    0.08
     Indoor
    0.07
     nons
    0.07
     cigarettes
    0.07
    Activations Density 0.020%

    No Known Activations