© 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. 5-LLAMASCOPE-RES-131K
    11. 125501
    Prev
    Next
    INDEX
    Explanations

    terms related to driving growth or forward momentum

    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
    ipple
    -0.06
    outs
    -0.06
     indications
    -0.06
    rypt
    -0.06
    old
    -0.06
    ilton
    -0.06
     for
    -0.06
    aron
    -0.06
    lis
    -0.06
     approach
    -0.05
    POSITIVE LOGITS
     vás
    0.08
    PLIED
    0.08
    Äįan
    0.07
    asse
    0.07
    inski
    0.07
    -toggler
    0.07
    OMEM
    0.07
    еÑĢеж
    0.07
    ColumnType
    0.07
    lesc
    0.07
    Activations Density 0.003%

    No Known Activations