© 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. 93222
    Prev
    Next
    INDEX
    Explanations

    keywords related to organizational structure and relationships within companies

    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
    adol
    -0.08
    uling
    -0.08
    ampa
    -0.07
    asto
    -0.07
    omik
    -0.07
     меÑĢ
    -0.07
    ahir
    -0.07
    ÑĢаÑĤно
    -0.07
    reur
    -0.07
    /react
    -0.07
    POSITIVE LOGITS
     trough
    0.06
     harmless
    0.06
     è¦
    0.06
     apparent
    0.06
     Morr
    0.05
    rical
    0.05
     wet
    0.05
     dü
    0.05
    nick
    0.05
    _ta
    0.05
    Activations Density 0.004%

    No Known Activations