© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 76096
    Prev
    Next
    INDEX
    Explanations

    phrases related to effective practices and evaluations in programs or interventions

    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
    à¥įदर
    -0.06
    CLUDING
    -0.06
     cen
    -0.06
     RAW
    -0.06
    loh
    -0.06
    lass
    -0.06
    erra
    -0.06
    ioni
    -0.06
    æ³ī
    -0.06
     coll
    -0.05
    POSITIVE LOGITS
     best
    0.10
     effective
    0.10
     Effective
    0.10
     successful
    0.09
    best
    0.09
    successful
    0.09
     beste
    0.09
     effectiveness
    0.09
    Effective
    0.09
     Successful
    0.09
    Activations Density 0.026%

    No Known Activations