© 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. 15579
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "ay" and its variations, indicating a focus on references related to celebration or events

    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
    sy
    -0.09
    su
    -0.09
    sch
    -0.08
    sell
    -0.08
    sil
    -0.08
    sen
    -0.08
    sein
    -0.07
    sie
    -0.07
    s
    -0.07
    د
    -0.07
    POSITIVE LOGITS
    urved
    0.09
    eb
    0.09
    ton
    0.08
    theon
    0.08
    yyyy
    0.08
    den
    0.08
    ÑĤеÑģÑĮ
    0.08
    ÌĪ
    0.08
    ebi
    0.08
    ev
    0.08
    Activations Density 0.081%

    No Known Activations