© 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. 2667
    Prev
    Next
    INDEX
    Explanations

    phrases with contrasting concepts or dualities

    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
    _Tis
    -0.11
    _Lean
    -0.10
    ÌĨ
    -0.10
    ]={↵
    -0.10
     sỼm
    -0.10
    OrNil
    -0.09
    .createClass
    -0.09
    ellas
    -0.09
    regor
    -0.09
    Ģ
    -0.09
    POSITIVE LOGITS
     etc
    0.08
    ;
    0.08
    .
    0.07
    ?
    0.06
    ..
    0.06
     Lang
    0.06
    etc
    0.06
     again
    0.06
     all
    0.06
     bar
    0.06
    Activations Density 0.019%

    No Known Activations