© 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. 15-LLAMASCOPE-RES-131K
    11. 104282
    Prev
    Next
    INDEX
    Explanations

    themes related to conflict and divorce

    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
    ropa
    -0.07
     Hüs
    -0.06
    naires
    -0.06
    :Register
    -0.06
    åħµ
    -0.06
    lier
    -0.06
    locales
    -0.06
    è·Ŀ
    -0.06
    leon
    -0.06
    _mux
    -0.06
    POSITIVE LOGITS
    spe
    0.09
     speaker
    0.09
    -spe
    0.08
     speakers
    0.07
     speaking
    0.07
     speak
    0.07
     heck
    0.07
    -speaking
    0.07
     speaks
    0.06
     talks
    0.06
    Activations Density 0.006%

    No Known Activations