© 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. 118663
    Prev
    Next
    INDEX
    Explanations

    themes of personal relationships and emotional struggles

    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
    ekli
    -0.08
     nues
    -0.08
    raki
    -0.07
     Чи
    -0.07
    istra
    -0.07
    uada
    -0.07
     çŁ
    -0.07
    izophren
    -0.07
    roker
    -0.07
    pora
    -0.07
    POSITIVE LOGITS
    ophil
    0.06
    iew
    0.06
     masturb
    0.06
    203
    0.06
    ook
    0.06
     memor
    0.06
     conf
    0.06
    apt
    0.05
     collection
    0.05
     watching
    0.05
    Activations Density 0.017%

    No Known Activations