© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 92414
    Prev
    Next
    INDEX
    Explanations

    expressions of social justice and accountability themes

    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
    oir
    -0.09
    leftright
    -0.08
    ãĥ¼ãĥģ
    -0.07
    event
    -0.07
    ãĥ¼ãĤ¸
    -0.07
     later
    -0.07
    æĿ¿
    -0.07
    imeline
    -0.07
    erglass
    -0.07
    ίκ
    -0.07
    POSITIVE LOGITS
     seriously
    0.06
     finally
    0.06
    rett
    0.06
     artık
    0.06
     overdue
    0.06
     serious
    0.06
    zu
    0.06
     officially
    0.05
    ãĤĤãģĨ
    0.05
     conhe
    0.05
    Activations Density 0.034%

    No Known Activations