© 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. 128186
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Carol" in various contexts

    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
    etary
    -0.08
    yon
    -0.08
    yi
    -0.08
    λή
    -0.07
    erty
    -0.07
    oracle
    -0.07
    \<^
    -0.07
    ess
    -0.07
    elor
    -0.07
    kie
    -0.06
    POSITIVE LOGITS
    thers
    0.08
     dÄ±ÅŁÄ±
    0.08
    ause
    0.07
    igua
    0.07
    ians
    0.07
    pus
    0.07
    ving
    0.07
    shed
    0.07
    lsen
    0.07
    son
    0.07
    Activations Density 0.001%

    No Known Activations