© 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. 39098
    Prev
    Next
    INDEX
    Explanations

    themes related to human rights and their implications

    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
    ardi
    -0.07
    ime
    -0.06
    arger
    -0.06
    oders
    -0.06
    itta
    -0.06
     pers
    -0.06
    ernet
    -0.06
    ysi
    -0.06
    _fold
    -0.06
    PLICIT
    -0.05
    POSITIVE LOGITS
     decisions
    0.11
     affects
    0.10
     affect
    0.10
    ffect
    0.09
     quyết
    0.09
     decision
    0.09
     affecting
    0.09
    決å®ļ
    0.09
    ffects
    0.09
    åĨ³å®ļ
    0.08
    Activations Density 0.033%

    No Known Activations