© 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. 3461
    Prev
    Next
    INDEX
    Explanations

    terms related to the adult entertainment industry and associated legal restrictions

    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
     dash
    -0.07
    ÏĬ
    -0.07
    ansi
    -0.06
     sass
    -0.06
     persec
    -0.06
     Bald
    -0.06
     Beard
    -0.06
    PD
    -0.06
    PEED
    -0.06
    æģµ
    -0.06
    POSITIVE LOGITS
     content
    0.08
    -content
    0.07
     Content
    0.07
    irector
    0.07
    tainment
    0.07
     harms
    0.06
    ECTOR
    0.06
    çŃ
    0.06
    apons
    0.06
    EXTERN
    0.06
    Activations Density 0.002%

    No Known Activations