© 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 EvalsExportsinterp-engineNEWAPI 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. 73283
    Prev
    Next
    INDEX
    Explanations

    topics related to women's roles in the workforce and the challenges they face

    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
    OLOR
    -0.06
    .aspx
    -0.06
    ordo
    -0.06
    ema
    -0.06
    itage
    -0.06
    dra
    -0.06
     oppressed
    -0.06
    CCCCCC
    -0.06
    _indices
    -0.06
    xls
    -0.06
    POSITIVE LOGITS
     invis
    0.07
     hourly
    0.07
    ÑģÑıÑĤ
    0.07
     prec
    0.07
     fil
    0.07
     dán
    0.07
    hour
    0.06
     hazard
    0.06
     Paid
    0.06
     work
    0.06
    Activations Density 0.007%

    No Known Activations