© 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. 71867
    Prev
    Next
    INDEX
    Explanations

    phrases indicating difficulty or uncertainty

    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
    757
    -0.07
     whom
    -0.06
    kara
    -0.06
    _PROTOCOL
    -0.06
    åħ¶ä¸Ń
    -0.06
    bove
    -0.06
     Halk
    -0.06
     beled
    -0.06
    759
    -0.06
    iaux
    -0.06
    POSITIVE LOGITS
    ertino
    0.07
    iedo
    0.07
    linger
    0.06
    ãĥ³ãĤº
    0.06
    æ¯ķ
    0.06
    ॰
    0.06
    ardo
    0.06
     something
    0.06
    езд
    0.06
    erus
    0.06
    Activations Density 0.051%

    No Known Activations