© 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. 129244
    Prev
    Next
    INDEX
    Explanations

    instances of the word "has" in various 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
    olib
    -0.07
    ÑĸÑģÑĤ
    -0.07
     ET
    -0.06
    SourceType
    -0.06
     clue
    -0.06
    .bio
    -0.06
     èĩ³
    -0.06
    enzyme
    -0.06
    γα
    -0.06
    eturn
    -0.06
    POSITIVE LOGITS
     dou
    0.07
    utely
    0.07
    IPA
    0.07
    ĵåIJį
    0.06
    alker
    0.06
    unken
    0.06
    alsy
    0.06
    htags
    0.06
    //===
    0.06
    acus
    0.06
    Activations Density 0.011%

    No Known Activations