© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 128639
    Prev
    Next
    INDEX
    Explanations

    terms related to gender identity and expressions of gender

    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
    olit
    -0.07
    yms
    -0.07
    lla
    -0.07
    iske
    -0.07
    kus
    -0.07
    amins
    -0.06
    hea
    -0.06
    uce
    -0.06
    odyn
    -0.06
    isko
    -0.06
    POSITIVE LOGITS
     identifying
    0.07
     congr
    0.06
     fundamentally
    0.06
    èķī
    0.06
     internally
    0.06
     appropri
    0.06
     identity
    0.06
    _identity
    0.06
     early
    0.06
     Ùħرتب
    0.06
    Activations Density 0.003%

    No Known Activations