© 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 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. 15-LLAMASCOPE-RES-131K
    11. 88472
    Prev
    Next
    INDEX
    Explanations

    concepts related to prioritization and decision-making in the context of personal and societal choices

    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
    stell
    -0.08
     totiž
    -0.07
    omik
    -0.07
    roperty
    -0.07
    okino
    -0.07
    ázd
    -0.07
    UpInside
    -0.07
    ¦¬
    -0.06
    bourg
    -0.06
    agnostic
    -0.06
    POSITIVE LOGITS
     others
    0.16
    others
    0.12
     Others
    0.11
     ones
    0.11
     those
    0.10
    Others
    0.09
     other
    0.09
     Those
    0.09
     Ones
    0.08
     naopak
    0.08
    Activations Density 0.022%

    No Known Activations