© 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. 73637
    Prev
    Next
    INDEX
    Explanations

    concepts related to legal liability and agency

    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
     سÙĨت
    -0.07
    aiser
    -0.07
    malink
    -0.07
     mastur
    -0.07
    otto
    -0.07
    į°
    -0.07
    رÙĪÛĮ
    -0.07
    å·ŀå¸Ĥ
    -0.07
    cape
    -0.07
    láš
    -0.07
    POSITIVE LOGITS
     reasonable
    0.08
     knew
    0.08
     knowledge
    0.08
     reasonably
    0.06
    rew
    0.06
    лива
    0.06
    ff
    0.06
     known
    0.06
     superv
    0.06
     floods
    0.06
    Activations Density 0.021%

    No Known Activations