© 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. 95510
    Prev
    Next
    INDEX
    Explanations

    references to a person named Carly or similar variations of the name

    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
    ίθ
    -0.07
    fred
    -0.06
    846
    -0.06
    vie
    -0.06
    esso
    -0.06
    icaret
    -0.06
    abo
    -0.06
     Wich
    -0.06
    Ậ
    -0.06
    busters
    -0.06
    POSITIVE LOGITS
    brook
    0.07
    er
    0.07
    ateg
    0.06
     Dra
    0.06
    e
    0.06
     cra
    0.06
    ãģıãĤĵ
    0.06
    UNS
    0.06
     Nic
    0.06
    anch
    0.06
    Activations Density 0.004%

    No Known Activations