© 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. 70202
    Prev
    Next
    INDEX
    Explanations

    phrases indicating negative consequences or concerns related to actions and their impacts

    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
     کارÛĮ
    -0.07
     Otherwise
    -0.07
    olas
    -0.07
     бÑĥдÑĮ
    -0.07
    CUS
    -0.07
    باد
    -0.06
    Fcn
    -0.06
    _SF
    -0.06
    ÙĨج
    -0.06
    .getBytes
    -0.06
    POSITIVE LOGITS
     even
    0.08
     further
    0.08
     actually
    0.08
     also
    0.07
    eshire
    0.07
    even
    0.07
     next
    0.07
     recently
    0.07
     kicker
    0.07
    perf
    0.06
    Activations Density 0.027%

    No Known Activations