© 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 EvalsExportsinterp-engineNEWAPI 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. 97481
    Prev
    Next
    INDEX
    Explanations

    instances of the word "alone."

    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
    ei
    -0.07
    -ÑĤо
    -0.07
    seite
    -0.07
    AGMA
    -0.06
    dat
    -0.06
    opensource
    -0.06
    -Encoding
    -0.06
    виÑĤ
    -0.06
    lys
    -0.06
    /ph
    -0.06
    POSITIVE LOGITS
    alone
    0.07
    ucid
    0.07
    Tester
    0.07
    éľĢ
    0.07
    arrow
    0.07
    inas
    0.07
    itudes
    0.06
    adders
    0.06
    sns
    0.06
    повÑĸд
    0.06
    Activations Density 0.008%

    No Known Activations