© 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. 17-LLAMASCOPE-RES-131K
    11. 16450
    Prev
    Next
    INDEX
    Explanations

    mentions of organization dynamics, particularly related to positions and roles within groups

    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
     subur
    -0.09
    _ALIGNMENT
    -0.08
    elden
    -0.08
     kvinne
    -0.08
    readcr
    -0.08
     subrange
    -0.08
    Smarty
    -0.07
     ruku
    -0.07
    iddi
    -0.07
    ë²Ħì§Ģ
    -0.07
    POSITIVE LOGITS
     altogether
    0.15
     entirely
    0.09
     because
    0.08
     completely
    0.08
     Alto
    0.07
     after
    0.07
     unless
    0.07
    å¹»
    0.06
    0.06
     except
    0.06
    Activations Density 0.111%

    No Known Activations