© 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. 42277
    Prev
    Next
    INDEX
    Explanations

    phrases related to disclaimers and the accuracy of information

    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
    ilon
    -0.07
    vert
    -0.06
     trespass
    -0.06
    br
    -0.05
    ,
    -0.05
    umm
    -0.05
     followed
    -0.05
     sum
    -0.05
     bake
    -0.05
     syn
    -0.05
    POSITIVE LOGITS
     accuracy
    0.09
    accuracy
    0.09
    MERCHANTABILITY
    0.08
     NONINFRINGEMENT
    0.08
     correctness
    0.08
    Accuracy
    0.08
    ugins
    0.08
    isÃŃ
    0.08
    chwitz
    0.08
    ubat
    0.07
    Activations Density 0.002%

    No Known Activations