© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 84788
    Prev
    Next
    INDEX
    Explanations

    terms related to criminal law and domestic violence

    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
    iveau
    -0.07
    ARRIER
    -0.07
    çĵľ
    -0.07
     clearColor
    -0.07
    nem
    -0.07
     رب
    -0.07
    mekte
    -0.07
    ÑģÑİ
    -0.07
    aryawan
    -0.07
    drž
    -0.07
    POSITIVE LOGITS
     conviction
    0.07
     convictions
    0.07
     lump
    0.06
     drug
    0.06
     apt
    0.06
     grounds
    0.06
     vaguely
    0.06
     punished
    0.06
    ç»ĵ
    0.06
     judges
    0.05
    Activations Density 0.007%

    No Known Activations