© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 9-LLAMASCOPE-RES-131K
    11. 97278
    Prev
    Next
    INDEX
    Explanations

    instances of the word "from."

    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
    issing
    -0.06
    ulings
    -0.06
    ilities
    -0.06
    chia
    -0.06
    Mixin
    -0.06
    kan
    -0.06
    lei
    -0.06
    çĭIJ
    -0.06
    ัà¸ķร
    -0.06
    äºŃ
    -0.06
    POSITIVE LOGITS
     exist
    0.07
    amura
    0.07
     being
    0.06
    _SCL
    0.06
    apest
    0.06
     existence
    0.06
    æĻ¯
    0.06
    _REDIRECT
    0.06
    Dot
    0.06
    orget
    0.06
    Activations Density 0.020%

    No Known Activations