© 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 EvalsExportsAPI 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. 118716
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Cory" and its variations in different 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
    tainment
    -0.09
    urd
    -0.08
    701
    -0.07
    IBE
    -0.07
    jeme
    -0.07
    ilion
    -0.07
    ร
    -0.07
    .scalablytyped
    -0.07
     Greenwood
    -0.07
    maids
    -0.06
    POSITIVE LOGITS
    aley
    0.07
    latin
    0.07
    нÑĤ
    0.07
    gro
    0.06
    ct
    0.06
    thus
    0.06
    eum
    0.06
     Conv
    0.06
    roller
    0.06
     conv
    0.06
    Activations Density 0.007%

    No Known Activations