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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 106455
    Prev
    Next
    INDEX
    Explanations

    dates and numerical values

    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
    Ģë¡ľ
    -0.07
    ;element
    -0.07
    ableView
    -0.06
    овоÑĢ
    -0.06
    InstanceState
    -0.06
     Scha
    -0.06
    лÑĸд
    -0.06
     pinterest
    -0.06
    ();++
    -0.06
    ymi
    -0.06
    POSITIVE LOGITS
    gtest
    0.06
    fte
    0.06
    Recorder
    0.06
    âng
    0.06
    ories
    0.06
    iem
    0.06
    oms
    0.06
    fen
    0.06
    ruc
    0.06
    561
    0.06
    Activations Density 0.000%

    No Known Activations