© 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. 92128
    Prev
    Next
    INDEX
    Explanations

    negations and expressions related to restrictions or limitations

    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
     thr
    -0.07
    oes
    -0.06
    als
    -0.06
     FactoryBot
    -0.06
    ongsTo
    -0.06
     boring
    -0.06
    اÙĩÛĮ
    -0.06
    ìĨį
    -0.06
    èµĦ
    -0.06
    bes
    -0.06
    POSITIVE LOGITS
    allowed
    0.10
     allowed
    0.10
    åħģ
    0.09
    ALLOW
    0.08
    allow
    0.08
    Allowed
    0.08
     permitted
    0.08
     Allowed
    0.08
    ¡
    0.07
     allow
    0.07
    Activations Density 0.029%

    No Known Activations