© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 96540
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate roles or identities within organizational or professional contexts

    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
    angan
    -0.07
    å½¹
    -0.07
    cheid
    -0.07
    øre
    -0.07
     zg
    -0.07
    immel
    -0.07
    cko
    -0.07
    venir
    -0.06
    croft
    -0.06
    izon
    -0.06
    POSITIVE LOGITS
    556
    0.07
    .bel
    0.06
     thuis
    0.06
    ırak
    0.06
     Affairs
    0.05
    564
    0.05
     extr
    0.05
    uer
    0.05
     “
    0.05
    802
    0.05
    Activations Density 0.019%

    No Known Activations