© 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. 95108
    Prev
    Next
    INDEX
    Explanations

    phrases related to player positions and their roles in sports

    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
    ̧
    -0.07
    ikh
    -0.07
    akah
    -0.07
    anko
    -0.07
    andbox
    -0.07
    orsk
    -0.07
    bris
    -0.07
    plet
    -0.07
    åĩ½
    -0.07
    avad
    -0.07
    POSITIVE LOGITS
    olog
    0.07
     trad
    0.06
     corre
    0.06
     unspecified
    0.06
    ARP
    0.06
     position
    0.06
     supplementary
    0.06
    ,rp
    0.06
     positions
    0.05
     mountain
    0.05
    Activations Density 0.015%

    No Known Activations