© 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. 28214
    Prev
    Next
    INDEX
    Explanations

    phrases or structures associated with governmental or organizational authority

    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
     closure
    -0.07
     ÙħÛĮÙĦادÛĮ
    -0.06
     moderator
    -0.06
    ÑĪÑĮ
    -0.06
    mite
    -0.06
     pageSize
    -0.06
     nors
    -0.06
    closure
    -0.06
    apore
    -0.06
    ILT
    -0.06
    POSITIVE LOGITS
    letcher
    0.08
    575
    0.07
    osemite
    0.07
    erece
    0.07
    /rs
    0.07
    POCH
    0.06
    479
    0.06
    eteor
    0.06
    lder
    0.06
    692
    0.06
    Activations Density 0.024%

    No Known Activations