© 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. 29311
    Prev
    Next
    INDEX
    Explanations

    phrases that include the word "with" and its contexts

    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
    owie
    -0.07
    atte
    -0.07
    ascus
    -0.06
    ritel
    -0.06
    wig
    -0.06
    ãĥĭãĥ¼
    -0.06
    ulent
    -0.06
    âĢ¦↵↵↵
    -0.06
    elmet
    -0.06
     dess
    -0.06
    POSITIVE LOGITS
    unker
    0.07
    isser
    0.07
     slight
    0.06
     Wich
    0.06
     Kaiser
    0.06
     different
    0.06
    154
    0.06
    ewing
    0.06
    ook
    0.06
    ou
    0.06
    Activations Density 0.020%

    No Known Activations