© 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. 2725
    Prev
    Next
    INDEX
    Explanations

    key factors or criteria that organizations consider important

    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
     Pose
    -0.06
    ród
    -0.06
     Modes
    -0.06
    eyse
    -0.06
    allery
    -0.06
     McD
    -0.06
    fy
    -0.06
    _markup
    -0.05
    empor
    -0.05
     lately
    -0.05
    POSITIVE LOGITS
     criteria
    0.12
    Criteria
    0.12
    criteria
    0.12
     Criteria
    0.12
     criterion
    0.11
    riteria
    0.10
    _criteria
    0.10
     Criterion
    0.09
    Criterion
    0.09
     criter
    0.09
    Activations Density 0.096%

    No Known Activations