© 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. 75609
    Prev
    Next
    INDEX
    Explanations

    variations of the word "hold" in various contexts

    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
    DRV
    -0.08
    ched
    -0.06
     glyc
    -0.06
    asaki
    -0.06
    igte
    -0.06
    BackStack
    -0.06
    drive
    -0.06
    divide
    -0.06
    chant
    -0.06
    OnClickListener
    -0.06
    POSITIVE LOGITS
    over
    0.09
    ovan
    0.08
    iday
    0.07
    erness
    0.07
    ราà¸Ĭ
    0.07
    sic
    0.07
    .internet
    0.06
    eman
    0.06
    out
    0.06
    oba
    0.06
    Activations Density 0.008%

    No Known Activations