© 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. 94787
    Prev
    Next
    INDEX
    Explanations

    the presence of the word "check" in various contexts, indicating it is looking for references to checking or verifying information

    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
    itters
    -0.07
     ruku
    -0.07
    xes
    -0.06
     ruk
    -0.06
    stad
    -0.06
    acias
    -0.06
    heels
    -0.06
    оÑĩкÑĥ
    -0.06
    iaux
    -0.06
    acia
    -0.06
    POSITIVE LOGITS
     boxes
    0.08
    lists
    0.08
     box
    0.07
    ered
    0.07
     checks
    0.07
    boxes
    0.07
    -box
    0.07
    -in
    0.07
    kt
    0.07
     check
    0.06
    Activations Density 0.019%

    No Known Activations