© 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. 88549
    Prev
    Next
    INDEX
    Explanations

    phrases specifically related to women's achievements and representation

    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
    ASA
    -0.07
    frey
    -0.07
    caster
    -0.07
    ophage
    -0.07
    indows
    -0.07
    oque
    -0.07
    nger
    -0.07
    oad
    -0.07
    aldi
    -0.06
    ater
    -0.06
    POSITIVE LOGITS
    emos
    0.06
    ence
    0.06
    ampo
    0.06
     Overs
    0.06
    erot
    0.06
     Economic
    0.06
    oms
    0.06
    GNUC
    0.06
    æ¼¢
    0.06
    esto
    0.06
    Activations Density 0.010%

    No Known Activations