© 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. 72782
    Prev
    Next
    INDEX
    Explanations

    phrases related to transitions or changes in state

    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
    strt
    -0.08
    ntag
    -0.07
    iras
    -0.07
    imei
    -0.07
    rze
    -0.07
    esthesia
    -0.07
    uby
    -0.07
    unda
    -0.06
    neas
    -0.06
    ecta
    -0.06
    POSITIVE LOGITS
    -step
    0.09
     Steph
    0.09
     step
    0.09
    step
    0.09
    .step
    0.08
     Shoes
    0.08
     Step
    0.08
     shoes
    0.08
     toes
    0.08
     stepped
    0.07
    Activations Density 0.009%

    No Known Activations