© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 103494
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize the importance of a situation or outcome

    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
    addtogroup
    -0.07
    uter
    -0.07
    stin
    -0.07
    ilent
    -0.07
    alie
    -0.07
    oples
    -0.07
    ille
    -0.07
    ãģĤãĤĭ
    -0.07
    sko
    -0.07
    оÑĥ
    -0.07
    POSITIVE LOGITS
     whether
    0.11
    whether
    0.09
     anymore
    0.09
     Whether
    0.08
    375
    0.07
    Whether
    0.07
    545
    0.07
    æĺ¯åIJ¦
    0.07
     how
    0.07
     nor
    0.06
    Activations Density 0.005%

    No Known Activations