© 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. 94984
    Prev
    Next
    INDEX
    Explanations

    references to celestial bodies and divine elements

    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
    ities
    -0.07
    ed
    -0.07
    ells
    -0.07
    edly
    -0.06
    able
    -0.06
    z
    -0.06
     exc
    -0.06
     segment
    -0.06
    es
    -0.06
    inant
    -0.06
    POSITIVE LOGITS
    Äįit
    0.08
    ãĤ¦ãĤ¹
    0.08
    å¾Ģ
    0.08
     seni
    0.08
     Král
    0.07
    ÏĦοκ
    0.07
    izoph
    0.07
    ColumnType
    0.07
     serialVersionUID
    0.07
    contri
    0.07
    Activations Density 0.008%

    No Known Activations