© 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 EvalsExportsAPI 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. 85852
    Prev
    Next
    INDEX
    Explanations

    elements related to ethical discussions and social issues

    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
    ibo
    -0.07
    ilege
    -0.07
     same
    -0.07
    alty
    -0.07
     FactoryBot
    -0.06
    474
    -0.06
    451
    -0.06
    丸
    -0.06
    (equalTo
    -0.05
     Suicide
    -0.05
    POSITIVE LOGITS
    (ed
    0.07
    rog
    0.07
     Role
    0.07
    à¹Ĥร
    0.07
    û
    0.07
     probl
    0.07
    owered
    0.06
    _refer
    0.06
    uya
    0.06
     essentials
    0.06
    Activations Density 0.052%

    No Known Activations