© 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 EvalsExportsinterp-engineNEWAPI 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. 61994
    Prev
    Next
    INDEX
    Explanations

    themes of loss and emotional struggle

    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
    uckle
    -0.06
     Kale
    -0.06
     oltre
    -0.06
    íĺ¸
    -0.06
    bes
    -0.06
    hya
    -0.06
     Berger
    -0.05
    elho
    -0.05
    678
    -0.05
    kv
    -0.05
    POSITIVE LOGITS
    phies
    0.07
    едж
    0.07
    croft
    0.07
    udios
    0.06
    iffin
    0.06
     Ñīодо
    0.06
    adio
    0.06
    ãĥĥãĤ¯ãĤ¹
    0.06
    .TestTools
    0.06
    .scalablytyped
    0.06
    Activations Density 0.047%

    No Known Activations