© 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. 129407
    Prev
    Next
    INDEX
    Explanations

    aspects related to game time, particularly goals and the remaining minutes in a match

    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
    hari
    -0.08
    anka
    -0.07
    .club
    -0.07
    ripper
    -0.07
    hatt
    -0.07
    ignum
    -0.07
    ãĥ¼ãĤº
    -0.07
    Âłmi
    -0.07
    ivent
    -0.06
    EDIA
    -0.06
    POSITIVE LOGITS
    luent
    0.06
    uppet
    0.06
    ArrayOf
    0.06
    ä»ķ
    0.06
     иÑģ
    0.06
    vinc
    0.06
    ãĤ¦ãĥ³
    0.06
    steen
    0.06
    obil
    0.06
    cea
    0.06
    Activations Density 0.011%

    No Known Activations