© 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. 17-LLAMASCOPE-RES-131K
    6. 16106
    Prev
    Next
    INDEX
    Explanations

    references to policies aimed at reducing alcohol consumption and its associated harms

    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
    adge
    -0.08
    allah
    -0.07
     Hatch
    -0.07
     persec
    -0.06
    olet
    -0.06
    geber
    -0.06
    æ°ı
    -0.06
    phere
    -0.06
    adÃŃ
    -0.06
     sond
    -0.06
    POSITIVE LOGITS
     harm
    0.08
    наÑĢ
    0.08
     MDMA
    0.07
     наÑĢ
    0.07
    stasy
    0.07
     nar
    0.07
     harms
    0.07
     Harm
    0.07
     заклад
    0.06
    ahat
    0.06
    Activations Density 0.012%

    No Known Activations