© 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. 95146
    Prev
    Next
    INDEX
    Explanations

    instances of the word "had" 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
    auf
    -0.07
    éĢ¸
    -0.07
     hereby
    -0.07
     currently
    -0.07
    alim
    -0.07
    datatable
    -0.06
    ABEL
    -0.06
    <KeyValuePair
    -0.06
     now
    -0.06
    eldom
    -0.06
    POSITIVE LOGITS
     earlier
    0.12
     originally
    0.10
     Earlier
    0.08
    origin
    0.08
     yesterday
    0.08
    Earlier
    0.08
    nt
    0.08
     ÑĢанÑĮÑĪе
    0.07
    Originally
    0.07
     سابÙĤ
    0.07
    Activations Density 0.061%

    No Known Activations