© 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. 124339
    Prev
    Next
    INDEX
    Explanations

    references to legal accountability 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
    Ưá»
    -0.07
    Ñīа
    -0.06
     Bir
    -0.06
     ÐŁÐ¾Ðº
    -0.06
    indsight
    -0.06
     æĻ®
    -0.06
     Pok
    -0.06
    folio
    -0.06
    æĻ®
    -0.06
     neutr
    -0.06
    POSITIVE LOGITS
     charged
    0.09
     Charg
    0.08
     facing
    0.07
     charges
    0.07
    _traits
    0.07
    uze
    0.07
    charged
    0.06
     conviction
    0.06
     Charges
    0.06
    -facing
    0.06
    Activations Density 0.040%

    No Known Activations