© 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. 84313
    Prev
    Next
    INDEX
    Explanations

    references to social justice topics, particularly focusing on LGBTQ+ issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    End-of-content markers or delimiters, often appearing in programming code, at the end of documents, or as section boundaries.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    Posted
    -0.10
     Posted
    -0.09
     tagged
    -0.07
     Tag
    -0.07
    enor
    -0.07
    -tag
    -0.07
    egis
    -0.07
     SHARES
    -0.07
    .TAG
    -0.07
    tag
    -0.07
    POSITIVE LOGITS
    yo
    0.07
     Candid
    0.06
    ui
    0.06
     Ned
    0.06
     Zwe
    0.06
    YO
    0.06
    алÑĮне
    0.06
     Ness
    0.06
     Pussy
    0.06
     minlength
    0.06
    Activations Density 0.032%

    No Known Activations