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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 61728
    Prev
    Next
    INDEX
    Explanations

    mentions of prescriptions and medical consultations

    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
     Deck
    -0.07
    lej
    -0.07
    lesai
    -0.06
    lei
    -0.06
    ëĿ¼ëıĦ
    -0.06
    CLR
    -0.06
    leon
    -0.06
    .contract
    -0.06
    .tasks
    -0.06
    dash
    -0.06
    POSITIVE LOGITS
    andas
    0.07
    Fullscreen
    0.06
    ammen
    0.06
     Jos
    0.06
    auer
    0.06
     {{{
    0.06
     Koch
    0.06
    elho
    0.06
     dispens
    0.06
    alborg
    0.06
    Activations Density 0.009%

    No Known Activations