© 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. 9-LLAMASCOPE-RES-131K
    11. 96858
    Prev
    Next
    INDEX
    Explanations

    references to accountability and actions taken by individuals or groups in response to 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
    kop
    -0.08
    atica
    -0.07
    kre
    -0.07
    %C
    -0.07
    odor
    -0.07
    udson
    -0.07
    aman
    -0.07
    ALCHEMY
    -0.07
    arget
    -0.07
    elsif
    -0.07
    POSITIVE LOGITS
     chance
    0.06
     togg
    0.05
    ļĮ
    0.05
    vents
    0.05
    0.05
    ØŃب
    0.05
     miser
    0.05
     alg
    0.05
     Morales
    0.05
     patch
    0.05
    Activations Density 0.000%

    No Known Activations