© 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. 59493
    Prev
    Next
    INDEX
    Explanations

    exclamatory statements and invitations to engage emotionally

    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
     thus
    -0.09
     also
    -0.08
     therefore
    -0.07
     hence
    -0.07
    åĽłæѤ
    -0.07
     ëķĮ문ìĹIJ
    -0.06
    ä¹Łæľī
    -0.06
     seh
    -0.06
    _CAST
    -0.06
     ayrıca
    -0.06
    POSITIVE LOGITS
    umu
    0.07
    rosso
    0.07
    ews
    0.07
    ãĤĩ
    0.06
    antry
    0.06
    ount
    0.06
    vary
    0.06
    fdb
    0.06
     nackte
    0.06
    zos
    0.06
    Activations Density 0.031%

    No Known Activations