© 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. 79978
    Prev
    Next
    INDEX
    Explanations

    terms related to historical figures and social justice themes

    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
    ixin
    -0.07
    raç
    -0.07
    bart
    -0.07
    erli
    -0.07
    umbn
    -0.07
     intox
    -0.06
    Ñıм
    -0.06
    éĨ
    -0.06
    locker
    -0.06
     ydk
    -0.06
    POSITIVE LOGITS
     underground
    0.14
     Underground
    0.12
     clandest
    0.10
     secret
    0.10
     hiding
    0.10
     Stealth
    0.09
    åľ°ä¸ĭ
    0.09
     hid
    0.08
     risks
    0.08
     Sne
    0.08
    Activations Density 0.047%

    No Known Activations