© 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. 79139
    Prev
    Next
    INDEX
    Explanations

    periods and punctuation indicating the end of thoughts or sentences

    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
    lection
    -0.06
    iner
    -0.06
    bring
    -0.06
    еÑĢÑĪ
    -0.06
     Mage
    -0.06
    коÑĢ
    -0.06
    DT
    -0.05
    996
    -0.05
    絡
    -0.05
    ports
    -0.05
    POSITIVE LOGITS
    Contained
    0.08
    åħ¶ä¸Ń
    0.08
     contains
    0.08
     contents
    0.08
     reads
    0.08
     containing
    0.08
     copp
    0.08
    reads
    0.08
     contain
    0.07
    contains
    0.07
    Activations Density 0.036%

    No Known Activations