© 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. 88979
    Prev
    Next
    INDEX
    Explanations

    terms related to law enforcement and criminal activity

    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
     pinch
    -0.07
    avig
    -0.06
     unfavorable
    -0.06
    assin
    -0.06
     Fox
    -0.06
     unfavor
    -0.06
     shitty
    -0.06
    021
    -0.06
    019
    -0.05
     Fol
    -0.05
    POSITIVE LOGITS
    .NewRequest
    0.08
    ?type
    0.07
    oire
    0.07
    -scrollbar
    0.07
    igua
    0.07
    ione
    0.07
    inite
    0.07
    絡
    0.07
    ereum
    0.07
    ÑĥÑĩа
    0.07
    Activations Density 0.001%

    No Known Activations