© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 27203
    Prev
    Next
    INDEX
    Explanations

    phrases related to understanding and comprehension

    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
    ål
    -0.07
    inel
    -0.07
    ynet
    -0.07
    /an
    -0.07
    essim
    -0.06
    ichten
    -0.06
    rof
    -0.06
    utar
    -0.06
    enal
    -0.06
    oa
    -0.06
    POSITIVE LOGITS
     ActionTypes
    0.08
     ///<
    0.07
    angan
    0.07
    ToLocal
    0.07
    ipse
    0.07
    UILTIN
    0.07
    HexString
    0.07
     actionTypes
    0.06
    /stats
    0.06
     Bron
    0.06
    Activations Density 0.010%

    No Known Activations