© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 84802
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate the presence of the word "with" 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
    HttpException
    -0.07
     Kirby
    -0.06
    okin
    -0.06
    ior
    -0.06
    ume
    -0.06
    ÑĢиÑģ
    -0.06
    ials
    -0.06
    CONTACT
    -0.06
    IODevice
    -0.06
     Neo
    -0.06
    POSITIVE LOGITS
     finishes
    0.07
    OTH
    0.06
    anzi
    0.06
    apia
    0.06
     finishing
    0.06
     holdings
    0.06
     win
    0.06
    äll
    0.06
    rica
    0.06
    finish
    0.06
    Activations Density 0.011%

    No Known Activations