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

    Neuronpedia

    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. 61623
    Prev
    Next
    INDEX
    Explanations

    references to the character Holden Caulfield from "The Catcher in the Rye."

    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
    aoke
    -0.07
    _
    -0.06
    479
    -0.06
    raid
    -0.06
     hood
    -0.06
    GV
    -0.06
     divisor
    -0.06
    eam
    -0.06
    634
    -0.05
    iec
    -0.05
    POSITIVE LOGITS
    anela
    0.07
     Carousel
    0.07
    arakter
    0.07
     Ñĩа
    0.07
     Trout
    0.07
     Knicks
    0.07
     NYC
    0.07
    _Private
    0.07
     NY
    0.07
    دارÛĮ
    0.07
    Activations Density 0.002%

    No Known Activations