© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 2818
    Prev
    Next
    INDEX
    Explanations

    expressions of intense emotional reactions and physical responses

    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
     coll
    -0.07
     sais
    -0.06
    Äĥm
    -0.06
    cheid
    -0.06
    ISC
    -0.06
     Rein
    -0.06
    wrapped
    -0.06
    .addProperty
    -0.06
     Transitional
    -0.06
    FX
    -0.05
    POSITIVE LOGITS
    Margin
    0.06
    actionDate
    0.06
    .Tween
    0.06
    .scalablytyped
    0.06
    bery
    0.06
    ëĮĢ를
    0.06
     داش
    0.06
    oogle
    0.06
    itzer
    0.06
    cret
    0.06
    Activations Density 0.019%

    No Known Activations