© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 130090
    Prev
    Next
    INDEX
    Explanations

    references to global political issues and social challenges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    HTML/webpage markup indicating article titles, headings or navigation elements, often followed by author information or publication metadata.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    ô
    -0.06
    Canceled
    -0.06
    Âļ
    -0.06
    à¥Ģब
    -0.05
    Unsigned
    -0.05
    Âŀ
    -0.05
    (CC
    -0.05
    730
    -0.05
    fig
    -0.05
     paperwork
    -0.05
    POSITIVE LOGITS
    dech
    0.08
    argout
    0.07
    ekim
    0.07
    rouch
    0.07
     bekl
    0.07
    /XMLSchema
    0.07
    chio
    0.07
    ylon
    0.06
    onse
    0.06
    ourced
    0.06
    Activations Density 0.083%

    No Known Activations