© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 86207
    Prev
    Next
    INDEX
    Explanations

    references to sexual orientation, particularly discussions about being gay

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    ingleton
    -0.08
    cak
    -0.07
    _Static
    -0.07
    Configurer
    -0.07
    иÑĢа
    -0.07
    recision
    -0.07
    ".$_
    -0.07
    ierce
    -0.07
    (iOS
    -0.06
    DOMNode
    -0.06
    POSITIVE LOGITS
     or
    0.07
    OFF
    0.06
    edor
    0.06
     flat
    0.06
    stat
    0.06
    O
    0.06
    295
    0.06
     flatt
    0.06
    okes
    0.06
    ot
    0.06
    Activations Density 0.000%

    No Known Activations