© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 116390
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports recruitment and announcements

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    eniable
    -0.07
     ìĭľíĸī
    -0.07
    exus
    -0.07
    Serializable
    -0.06
    illance
    -0.06
    rics
    -0.06
     Maher
    -0.06
    αιδ
    -0.06
    regunta
    -0.06
    ailable
    -0.06
    POSITIVE LOGITS
     choice
    0.08
     commitment
    0.07
     signing
    0.07
    choice
    0.07
     Decision
    0.07
    commit
    0.06
     choosing
    0.06
     decision
    0.06
     signed
    0.06
    Signing
    0.06
    Activations Density 0.004%

    No Known Activations