© 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. 17-LLAMASCOPE-RES-131K
    11. 56009
    Prev
    Next
    INDEX
    Explanations

    words that express emotional states or 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
     relent
    -0.07
    ãģıãĤĭ
    -0.06
    bote
    -0.06
    rait
    -0.06
    ãģķãĤĮãĤĭ
    -0.06
    lanır
    -0.06
     explan
    -0.06
     undergo
    -0.06
    #=
    -0.06
    nett
    -0.06
    POSITIVE LOGITS
     been
    0.19
     Been
    0.17
    been
    0.16
    Been
    0.16
     BEEN
    0.14
     telah
    0.13
     hasn
    0.13
     haven
    0.12
    've
    0.12
    ’ve
    0.11
    Activations Density 0.192%

    No Known Activations