© 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. 77427
    Prev
    Next
    INDEX
    Explanations

    issues related to public health and environmental concerns

    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
    itel
    -0.07
     olsun
    -0.07
     inval
    -0.06
    ober
    -0.06
    efe
    -0.06
     madrid
    -0.06
    FI
    -0.06
     gelen
    -0.06
    PlainText
    -0.06
    eda
    -0.06
    POSITIVE LOGITS
     Unless
    0.11
    unless
    0.10
     unless
    0.10
     Danger
    0.09
     danger
    0.09
    Unless
    0.09
     dangerously
    0.08
     dangers
    0.08
     future
    0.08
    åį±
    0.08
    Activations Density 0.040%

    No Known Activations