© 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. 85038
    Prev
    Next
    INDEX
    Explanations

    phrases related to performance experiences and evaluations

    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
    太éĥİ
    -0.06
     business
    -0.06
     kino
    -0.06
    ane
    -0.06
     Crowley
    -0.06
     industrial
    -0.06
    ewood
    -0.06
    RAW
    -0.06
    legg
    -0.06
    éc
    -0.06
    POSITIVE LOGITS
     PERFORMANCE
    0.08
     Performance
    0.07
    performance
    0.07
    Performance
    0.07
    entai
    0.07
     performance
    0.07
    .performance
    0.07
    ãĥ¼ãĥŀ
    0.07
     underst
    0.07
     вим
    0.07
    Activations Density 0.004%

    No Known Activations