© 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. 15869
    Prev
    Next
    INDEX
    Explanations

    instances of subjective opinions or emotional experiences

    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
    idar
    -0.07
    laz
    -0.07
    ulk
    -0.06
    alf
    -0.06
    ual
    -0.06
    ingen
    -0.06
    дн
    -0.06
    antes
    -0.06
    esi
    -0.06
    hek
    -0.06
    POSITIVE LOGITS
    ocker
    0.07
     gore
    0.06
     moo
    0.06
    church
    0.06
    ilere
    0.06
     //@
    0.06
    оÑĪ
    0.06
     ingin
    0.06
    ppo
    0.06
    edral
    0.06
    Activations Density 0.037%

    No Known Activations