© 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. 93088
    Prev
    Next
    INDEX
    Explanations

    terms related to chartered accountants and professional qualifications

    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
    olet
    -0.08
     GOODMAN
    -0.07
    olicit
    -0.07
    aload
    -0.07
     zad
    -0.06
    zend
    -0.06
    adol
    -0.06
    mund
    -0.06
    asal
    -0.06
    ola
    -0.06
    POSITIVE LOGITS
     char
    0.07
     Char
    0.07
    .hm
    0.07
     cer
    0.06
    _iff
    0.06
    rypt
    0.06
    PCM
    0.06
    (Dictionary
    0.06
     exam
    0.06
     Royal
    0.06
    Activations Density 0.007%

    No Known Activations