© 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. 62242
    Prev
    Next
    INDEX
    Explanations

    topics related to demographics 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
     stuff
    -0.06
    aller
    -0.06
    pard
    -0.06
    utsch
    -0.06
    ennen
    -0.06
    ạch
    -0.06
    µ¬
    -0.06
    ekten
    -0.06
    ublish
    -0.06
    ombok
    -0.06
    POSITIVE LOGITS
    -wide
    0.09
    -based
    0.08
    wide
    0.07
    ãģ«ãģĬãģijãĤĭ
    0.07
    -level
    0.07
    åħ³äºİ
    0.07
     versions
    0.07
    ãģ«ãĤĪãĤĭ
    0.07
     version
    0.07
    ãģ§ãģ®
    0.07
    Activations Density 0.067%

    No Known Activations