© 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. 77923
    Prev
    Next
    INDEX
    Explanations

    the word "technically" and phrases regarding technical definitions or clarifications

    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
    /tos
    -0.08
    rof
    -0.06
    iddi
    -0.06
    htub
    -0.06
     Morton
    -0.06
    elin
    -0.06
    аннÑı
    -0.06
    [..
    -0.06
     usual
    -0.06
     Eg
    -0.06
    POSITIVE LOGITS
     speaking
    0.10
    -speaking
    0.10
    techn
    0.09
     technically
    0.08
    à¹ģล
    0.08
     anlamda
    0.07
    ially
    0.07
    ALLY
    0.07
     Speaking
    0.07
    HEMA
    0.07
    Activations Density 0.011%

    No Known Activations