Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 43612
    Prev
    Next
    INDEX
    Explanations

    terms related to transgender and non-binary identities

    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
    atsby
    -0.07
    roupon
    -0.07
    elo
    -0.07
    eln
    -0.07
    ongsTo
    -0.07
    tsy
    -0.07
    ivatel
    -0.07
    ewater
    -0.06
    tti
    -0.06
    åĤ³
    -0.06
    POSITIVE LOGITS
    vest
    0.12
    ph
    0.11
    gender
    0.11
    mas
    0.10
    sexual
    0.10
    gend
    0.10
    gende
    0.10
    g
    0.10
     rights
    0.10
     visibility
    0.09
    Activations Density 0.008%

    No Known Activations