© 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. 15651
    Prev
    Next
    INDEX
    Explanations

    phrases indicating progression or succession

    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
     fondo
    -0.07
    ync
    -0.06
    smouth
    -0.06
    اÙģر
    -0.06
    uther
    -0.06
     Podesta
    -0.06
    ewith
    -0.06
    ">//
    -0.06
     Bilim
    -0.06
    ettle
    -0.06
    POSITIVE LOGITS
    ander
    0.08
    andra
    0.08
    무
    0.07
    inci
    0.07
    toc
    0.07
    -generation
    0.06
    YRO
    0.06
    here
    0.06
    generation
    0.06
    ãĢħ
    0.06
    Activations Density 0.008%

    No Known Activations