© 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. 9-LLAMASCOPE-RES-131K
    11. 94542
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports qualifications and placements

    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
    otte
    -0.07
    ноÑĩ
    -0.07
    uben
    -0.06
    á»ĵng
    -0.06
    大åħ¨
    -0.06
    alue
    -0.06
    lesen
    -0.06
    zos
    -0.06
    zes
    -0.06
    iesen
    -0.06
    POSITIVE LOGITS
    ardi
    0.06
    chk
    0.06
    lung
    0.06
    íĻĶ를
    0.06
     overhead
    0.06
     next
    0.06
    ucken
    0.06
    ãĤĤãģĨ
    0.06
     RMS
    0.06
    ustry
    0.06
    Activations Density 0.006%

    No Known Activations