© 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. 130204
    Prev
    Next
    INDEX
    Explanations

    terms related to legal penalties and enforcement actions

    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
    atar
    -0.06
    /INFO
    -0.06
    UNKNOWN
    -0.06
    аÑĤаÑĢ
    -0.06
    PUTE
    -0.06
    PATCH
    -0.06
    vise
    -0.06
    ä¼ı
    -0.06
    éĢĢ
    -0.06
    istrovstvÃŃ
    -0.06
    POSITIVE LOGITS
    andle
    0.08
     failure
    0.08
     fail
    0.07
    fail
    0.07
     infra
    0.07
     bree
    0.07
     violations
    0.07
     viol
    0.07
     Fail
    0.07
     mist
    0.07
    Activations Density 0.020%

    No Known Activations