© 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. 15-LLAMASCOPE-RES-131K
    11. 183
    Prev
    Next
    INDEX
    Explanations

    instances of significant past actions or events

    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
    ichni
    -0.08
    iverz
    -0.07
    iversit
    -0.07
    acro
    -0.07
    .Cap
    -0.07
    alley
    -0.07
     Retirement
    -0.07
     Patch
    -0.06
    antu
    -0.06
    ırak
    -0.06
    POSITIVE LOGITS
     sch
    0.07
    å¡
    0.07
     featuring
    0.07
    ãĥ¼ãĤ¸
    0.06
    ipped
    0.06
    eton
    0.06
    ặn
    0.06
    Orm
    0.06
    ãĥ¼ãĥķ
    0.05
    otel
    0.05
    Activations Density 0.000%

    No Known Activations