© 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. 123709
    Prev
    Next
    INDEX
    Explanations

    elements related to job applications and academic positions

    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
    usk
    -0.07
    achu
    -0.06
    enk
    -0.06
     substituted
    -0.06
    eten
    -0.06
    itta
    -0.06
    ocab
    -0.06
    é«
    -0.06
     scho
    -0.06
    Ñıб
    -0.06
    POSITIVE LOGITS
     poss
    0.06
    licants
    0.06
    successful
    0.06
    Traits
    0.06
     duties
    0.06
    ulg
    0.06
     Bliss
    0.06
    sWith
    0.06
     successful
    0.06
     specifics
    0.06
    Activations Density 0.003%

    No Known Activations