© 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. 55122
    Prev
    Next
    INDEX
    Explanations

    references to baking and cake preparation

    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
     suspension
    -0.08
     susp
    -0.08
     Suspension
    -0.06
     Susp
    -0.06
     powder
    -0.06
     Powder
    -0.06
     Pole
    -0.06
    adder
    -0.06
    cord
    -0.05
    èĶµ
    -0.05
    POSITIVE LOGITS
     shallow
    0.08
     Gret
    0.07
    procs
    0.07
    LAY
    0.07
    ReuseIdentifier
    0.07
     rectangle
    0.06
     ê²
    0.06
    ','',
    0.06
     cavity
    0.06
    osg
    0.06
    Activations Density 0.005%

    No Known Activations