© 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. 42003
    Prev
    Next
    INDEX
    Explanations

    references to gender identity and inclusivity

    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
    otal
    -0.07
    UrlParser
    -0.07
    ogle
    -0.07
    опиÑģ
    -0.07
    arken
    -0.07
    iliar
    -0.07
     Guys
    -0.07
     dahi
    -0.07
    ì§Ģëħ¸
    -0.07
    èĢħçļĦ
    -0.07
    POSITIVE LOGITS
     those
    0.11
     yourself
    0.09
     myself
    0.08
     ourselves
    0.08
    éĤ£äºĽ
    0.08
    those
    0.08
     Those
    0.08
     Fare
    0.07
     the
    0.07
     Yourself
    0.07
    Activations Density 0.036%

    No Known Activations