© 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. 120246
    Prev
    Next
    INDEX
    Explanations

    information related to job opportunities and career advancement in the accounting and MRI technology fields

    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
    @js
    -0.11
    (çģ«
    -0.11
    (æľ¨
    -0.10
    imd
    -0.10
    âĻ¡
    -0.10
    ëį°ìĿ´íĬ¸
    -0.09
    ï¼Ĭ
    -0.09
    gnore
    -0.09
    ï¼ĭ
    -0.09
    ãģĵãĤĵãģ«
    -0.09
    POSITIVE LOGITS
    <|end_of_text|>
    0.06
    ism
    0.06
    o
    0.06
    ©
    0.06
    ora
    0.06
    inp
    0.06
    ander
    0.06
     E
    0.06
    âĢ¦↵
    0.05
    ia
    0.05
    Activations Density 0.005%

    No Known Activations