© 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. 89254
    Prev
    Next
    INDEX
    Explanations

    phrases indicating cessation or restriction of options or activities

    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
     yet
    -0.08
    yet
    -0.08
    ellas
    -0.08
    ãģ¾ãģł
    -0.07
     henüz
    -0.06
     Yet
    -0.06
     ìķĦì§ģ
    -0.06
     ancora
    -0.06
    sar
    -0.06
     still
    -0.06
    POSITIVE LOGITS
     anymore
    0.13
     nor
    0.09
     пÑĢеж
    0.07
    amarin
    0.07
    omba
    0.07
    -exclusive
    0.07
    acci
    0.06
    ouns
    0.06
     necessarily
    0.06
    ÏģÏĮÏĤ
    0.06
    Activations Density 0.036%

    No Known Activations