© 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. 16375
    Prev
    Next
    INDEX
    Explanations

    references to celebrities and fashion events

    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
    .PNG
    -0.08
     Ley
    -0.06
    ãİ
    -0.06
    uter
    -0.06
    isoft
    -0.06
     Stout
    -0.06
     sys
    -0.06
    sys
    -0.06
    ->[
    -0.06
    voie
    -0.06
    POSITIVE LOGITS
     parties
    0.09
    azine
    0.09
     Vogue
    0.08
     Confidential
    0.08
     cele
    0.08
     fashion
    0.08
     Vanity
    0.08
     celebrity
    0.07
     Fashion
    0.07
     Rehab
    0.07
    Activations Density 0.092%

    No Known Activations