© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 57106
    Prev
    Next
    INDEX
    Explanations

    references to raising awareness of societal issues and crises

    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
     Weinstein
    -0.06
    AGO
    -0.06
    quoi
    -0.06
     offend
    -0.06
    565
    -0.05
    SSIP
    -0.05
    CRET
    -0.05
     ex
    -0.05
    ool
    -0.05
     frontline
    -0.05
    POSITIVE LOGITS
     plight
    0.08
     importance
    0.08
     issues
    0.08
     fact
    0.07
    PointF
    0.07
     dangers
    0.07
     issue
    0.07
     Importance
    0.07
    wchar
    0.07
    çļĦéĹ®é¢ĺ
    0.07
    Activations Density 0.020%

    No Known Activations