© 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. 90663
    Prev
    Next
    INDEX
    Explanations

    tips related to event planning, creativity, and general advice for decision-making

    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
    ouz
    -0.08
    дап
    -0.07
    oze
    -0.06
    rive
    -0.06
    ignet
    -0.06
    rippling
    -0.06
    WM
    -0.06
    ProcessEvent
    -0.06
    istro
    -0.06
    WithName
    -0.06
    POSITIVE LOGITS
    å¦Ĥä½ķ
    0.08
    roe
    0.07
    how
    0.07
     approaching
    0.07
     how
    0.07
     successful
    0.07
     hvordan
    0.06
    erg
    0.06
     care
    0.06
    iec
    0.06
    Activations Density 0.013%

    No Known Activations