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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 3984
    Prev
    Next
    INDEX
    Explanations

    themes related to female empowerment and identity

    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
    mp
    -0.07
    наÑĢод
    -0.07
    ollow
    -0.06
     performed
    -0.06
     trace
    -0.06
     Barbar
    -0.06
    éļ
    -0.06
    .FLAG
    -0.06
    trace
    -0.06
     grouped
    -0.06
    POSITIVE LOGITS
     reachable
    0.08
     vast
    0.08
    éļª
    0.07
    -transitional
    0.07
     hostile
    0.07
    éĻ©
    0.07
     киÑĪ
    0.07
     accessible
    0.07
    place
    0.07
     breathable
    0.07
    Activations Density 0.089%

    No Known Activations