© 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. 120708
    Prev
    Next
    INDEX
    Explanations

    high-ranking individuals and their roles within organizations or government entities

    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
    ifest
    -0.07
    ldr
    -0.07
    глÑı
    -0.07
    overrides
    -0.07
    dba
    -0.07
    ãĥ«ãĥī
    -0.07
    å·
    -0.07
    æ¥Ń
    -0.06
    VERRIDE
    -0.06
     commanders
    -0.06
    POSITIVE LOGITS
     co
    0.09
     vice
    0.08
    åī¯
    0.08
     Vice
    0.07
    ierz
    0.07
    çŃĨ
    0.07
    inson
    0.07
     Deputy
    0.06
     aide
    0.06
     deputy
    0.06
    Activations Density 0.038%

    No Known Activations