© 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. 27922
    Prev
    Next
    INDEX
    Explanations

    content related to LGBTQ themes and genres

    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
    urette
    -0.09
    ekler
    -0.08
     Blonde
    -0.08
    amide
    -0.07
    ervas
    -0.07
    اØ
    -0.07
    rete
    -0.07
    ETO
    -0.07
    clas
    -0.07
    lis
    -0.07
    POSITIVE LOGITS
     Gazette
    0.07
    oen
    0.06
     character
    0.06
    peri
    0.06
    raith
    0.06
     denn
    0.06
     apprec
    0.06
    ÑĢаÑī
    0.05
     Perc
    0.05
     deg
    0.05
    Activations Density 0.024%

    No Known Activations