© 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. 5273
    Prev
    Next
    INDEX
    Explanations

    phrases related to questioning norms or expressing dissent

    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
    entric
    -0.07
    åłĤ
    -0.07
     unregister
    -0.06
     меж
    -0.06
    ην
    -0.06
     Verfügung
    -0.06
    .addElement
    -0.06
    Spatial
    -0.06
    isoft
    -0.06
    _HINT
    -0.06
    POSITIVE LOGITS
     problem
    0.15
    problem
    0.12
     Problem
    0.12
     proble
    0.10
     objection
    0.10
     problems
    0.10
    Problem
    0.10
    .problem
    0.10
    éĹ®é¢ĺ
    0.10
     problema
    0.10
    Activations Density 0.033%

    No Known Activations