© 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 EvalsExportsinterp-engineNEWAPI 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. 92382
    Prev
    Next
    INDEX
    Explanations

    names of football players and their interactions within match 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
    ntl
    -0.09
    Äįku
    -0.07
    važ
    -0.07
    nev
    -0.07
    783
    -0.07
    oÄį
    -0.06
    stdarg
    -0.06
    ooke
    -0.06
    ÑĨеп
    -0.06
    omer
    -0.06
    POSITIVE LOGITS
    ataka
    0.07
    owler
    0.06
    deaux
    0.06
    .infinity
    0.06
    atter
    0.06
     âĢ¦↵
    0.06
    _Msk
    0.05
    ķĮ
    0.05
    urrets
    0.05
     sovere
    0.05
    Activations Density 0.018%

    No Known Activations