© 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. 17-LLAMASCOPE-RES-131K
    11. 3495
    Prev
    Next
    INDEX
    Explanations

    instances of the word "said" and its variations

    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
    pons
    -0.07
    OPY
    -0.06
    gate
    -0.06
    imir
    -0.06
    ysz
    -0.06
    lio
    -0.06
     alle
    -0.06
    .Abstractions
    -0.05
    pon
    -0.05
     concerning
    -0.05
    POSITIVE LOGITS
     yesterday
    0.10
     today
    0.10
     Monday
    0.09
     Tuesday
    0.09
    Tuesday
    0.08
     Wednesday
    0.08
     Thursday
    0.08
    Monday
    0.07
     recently
    0.07
     TODAY
    0.07
    Activations Density 0.037%

    No Known Activations