© 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. 17-LLAMASCOPE-RES-131K
    11. 70241
    Prev
    Next
    INDEX
    Explanations

    phrases indicating registration or user participation

    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
    ulle
    -0.06
    flo
    -0.06
    uma
    -0.06
    ÐĿЯ
    -0.06
    ì
    -0.06
    otts
    -0.06
    gons
    -0.06
    åĨ
    -0.06
    pery
    -0.06
     Jako
    -0.06
    POSITIVE LOGITS
    loquent
    0.07
    ednou
    0.07
    à¹Ģหà¸Ļ
    0.06
    yd
    0.06
    .touches
    0.06
    aroo
    0.06
    olet
    0.06
    eft
    0.06
    oui
    0.06
    aban
    0.06
    Activations Density 0.001%

    No Known Activations