© 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. 97493
    Prev
    Next
    INDEX
    Explanations

    instances of the word "speak" 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
    /out
    -0.07
    readcr
    -0.07
    bred
    -0.07
    cks
    -0.07
    roit
    -0.07
    rien
    -0.07
    ecycle
    -0.06
    acades
    -0.06
    nÃŃ
    -0.06
     Hawth
    -0.06
    POSITIVE LOGITS
    erville
    0.08
    peare
    0.07
    neider
    0.07
    ONS
    0.07
    inded
    0.06
     âĹĦ
    0.06
    (#)
    0.06
     mặt
    0.06
     minded
    0.06
    /testify
    0.06
    Activations Density 0.049%

    No Known Activations