© 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. 125568
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "of [something]," indicating relationships or associations

    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
    igne
    -0.07
    ppe
    -0.07
    igin
    -0.07
    alf
    -0.06
    udi
    -0.06
    ëĿ½
    -0.06
    owell
    -0.06
    пион
    -0.06
    ledon
    -0.06
    è¡Ľ
    -0.06
    POSITIVE LOGITS
    echan
    0.08
    .dateFormat
    0.07
    ä¾
    0.06
    bies
    0.06
    DRAM
    0.06
    hdr
    0.06
    ãĥ¼ãĥĩ
    0.06
     #:
    0.06
    presso
    0.06
     dÆ°
    0.06
    Activations Density 0.001%

    No Known Activations