© 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. 94097
    Prev
    Next
    INDEX
    Explanations

    phrases and references related to LGBTQ+ themes and characters

    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
    achu
    -0.08
    theid
    -0.07
    panel
    -0.07
    unday
    -0.07
    .dtd
    -0.07
    usercontent
    -0.06
    impan
    -0.06
    urette
    -0.06
    ëĬ
    -0.06
    ÂŃs
    -0.06
    POSITIVE LOGITS
     series
    0.20
    ãĤ·ãĥªãĥ¼ãĤº
    0.18
    series
    0.16
     Series
    0.16
     serie
    0.15
    _series
    0.15
    -series
    0.14
    (series
    0.14
    ç³»åĪĹ
    0.14
    Series
    0.14
    Activations Density 0.019%

    No Known Activations