© 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. 28363
    Prev
    Next
    INDEX
    Explanations

    words that emphasize community and societal impact

    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
    roke
    -0.08
    venes
    -0.08
    unic
    -0.07
    знаÑĩа
    -0.07
    оÑĢож
    -0.07
    idor
    -0.07
    raison
    -0.07
    SYS
    -0.07
    zew
    -0.07
    оке
    -0.07
    POSITIVE LOGITS
     society
    0.07
     Carpenter
    0.07
    ãĥ¼ãĥ«ãĥī
    0.06
    779
    0.06
    alance
    0.06
     economy
    0.06
     Essays
    0.06
    åĺĽ
    0.06
    LAS
    0.06
    oki
    0.06
    Activations Density 0.057%

    No Known Activations