© 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. 9-LLAMASCOPE-RES-131K
    11. 96788
    Prev
    Next
    INDEX
    Explanations

    instances of the word "quite" 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
    ATRIX
    -0.07
    ucci
    -0.07
    halt
    -0.07
    uele
    -0.07
    rogram
    -0.06
    wahl
    -0.06
    lot
    -0.06
    ologne
    -0.06
    ald
    -0.06
    hal
    -0.06
    POSITIVE LOGITS
    -ÑĤаки
    0.10
    ırı
    0.07
    ìĶ©
    0.06
    von
    0.06
    Tcp
    0.06
    saldo
    0.06
    _topology
    0.06
    achu
    0.06
     handful
    0.06
    ι
    0.06
    Activations Density 0.006%

    No Known Activations