© 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 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. 15-LLAMASCOPE-RES-131K
    11. 88129
    Prev
    Next
    INDEX
    Explanations

    exclamatory expressions and strong emotional reactions

    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
    ات
    -0.07
    hs
    -0.06
    loor
    -0.06
     epic
    -0.06
    iam
    -0.06
    ec
    -0.06
     Woo
    -0.06
    nbsp
    -0.06
    cae
    -0.05
    ÅĻev
    -0.05
    POSITIVE LOGITS
    rane
    0.08
    nict
    0.08
    ooled
    0.07
    NAMESPACE
    0.07
    erator
    0.07
    ored
    0.07
    877
    0.07
    unami
    0.06
    _mE
    0.06
     Kore
    0.06
    Activations Density 0.011%

    No Known Activations