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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3954
    Prev
    Next
    INDEX
    Explanations

    explicit references to legal or formal proceedings, including statements and testimony

    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
    ombo
    -0.09
    ucas
    -0.09
     zbo
    -0.08
    inho
    -0.08
    боÑĤ
    -0.08
    zc
    -0.07
    ÑĪин
    -0.07
    oug
    -0.07
    ivant
    -0.07
    ÃŁe
    -0.07
    POSITIVE LOGITS
     by
    0.13
     oleh
    0.10
     تÙĪسط
    0.09
     bợi
    0.08
     from
    0.08
    çĶ±
    0.08
     ìĿĺíķ´
    0.07
    æĿ¥èĩª
    0.07
    by
    0.06
     بÙĪاسطة
    0.06
    Activations Density 0.122%

    No Known Activations