© 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. 107203
    Prev
    Next
    INDEX
    Explanations

    words indicating significance or prominence in various contexts

    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
    istrovstvÃŃ
    -0.08
    «a
    -0.07
    íı
    -0.07
    OffsetTable
    -0.07
    NewProp
    -0.07
    aza
    -0.07
    instanc
    -0.07
     corrid
    -0.07
    âķĿ
    -0.07
    /prom
    -0.07
    POSITIVE LOGITS
     first
    0.20
    第ä¸Ģ
    0.16
    first
    0.15
     첫
    0.14
     pierws
    0.14
    .first
    0.13
     eerste
    0.13
     第ä¸Ģ
    0.13
     erste
    0.13
    (first
    0.13
    Activations Density 0.001%

    No Known Activations