© 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. 95488
    Prev
    Next
    INDEX
    Explanations

    references to legal actions and implications involving Trump

    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
    mscorlib
    -0.07
    .system
    -0.07
    침
    -0.07
    PCP
    -0.07
    prus
    -0.07
    FAULT
    -0.07
     Dün
    -0.07
    .createClass
    -0.07
     Phelps
    -0.07
    Äĥr
    -0.06
    POSITIVE LOGITS
    å½
    0.06
     åĶ
    0.06
     immunity
    0.06
     gig
    0.06
    fuse
    0.06
    abr
    0.06
    AGMA
    0.06
    ny
    0.06
     Beg
    0.06
    uid
    0.06
    Activations Density 0.002%

    No Known Activations