© 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. 92623
    Prev
    Next
    INDEX
    Explanations

    elements related to pop culture and media references

    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
    anten
    -0.07
    isman
    -0.06
     undes
    -0.06
    iss
    -0.05
     vase
    -0.05
     Reform
    -0.05
    asket
    -0.05
    een
    -0.05
     Merry
    -0.05
    CEO
    -0.05
    POSITIVE LOGITS
    #ad
    0.10
    czy
    0.09
     LENG
    0.09
     보기
    0.08
    поÑĩ
    0.08
    #__
    0.07
    #ab
    0.07
     ÑĦай
    0.07
    producer
    0.07
    Porno
    0.07
    Activations Density 0.028%

    No Known Activations