© 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. 17-LLAMASCOPE-RES-131K
    11. 118700
    Prev
    Next
    INDEX
    Explanations

    phrases expressing skepticism or criticism regarding societal structures and justice systems

    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
    indrome
    -0.06
    avenport
    -0.06
     tomorrow
    -0.06
    imitives
    -0.05
    compare
    -0.05
     hopefully
    -0.05
    emoc
    -0.05
     Wonder
    -0.05
    isco
    -0.05
     should
    -0.05
    POSITIVE LOGITS
     actual
    0.19
     Actual
    0.17
    Actual
    0.17
    å®ŀéĻħ
    0.17
    actual
    0.16
     actually
    0.15
     reality
    0.15
    _actual
    0.14
    actually
    0.14
     practical
    0.13
    Activations Density 0.042%

    No Known Activations