© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 118468
    Prev
    Next
    INDEX
    Explanations

    references to a specific individual named Cayla Guillory

    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
    ảo
    -0.08
    aton
    -0.08
    ÑĪки
    -0.08
    ofile
    -0.07
    #ac
    -0.07
    rtl
    -0.07
    Ïį
    -0.07
     dép
    -0.07
    ,...↵↵
    -0.07
    iedo
    -0.07
    POSITIVE LOGITS
     Dalton
    0.05
    het
    0.05
    appen
    0.05
     åº
    0.05
    rol
    0.05
    ahr
    0.05
     bitter
    0.05
    ks
    0.05
     c
    0.05
    \-
    0.05
    Activations Density 0.000%

    No Known Activations