© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 85174
    Prev
    Next
    INDEX
    Explanations

    references to personal connections and relationships

    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
     Py
    -0.07
     dist
    -0.07
     d
    -0.06
    steen
    -0.06
     LS
    -0.06
     for
    -0.06
    lex
    -0.06
     clean
    -0.06
     tr
    -0.06
     with
    -0.06
    POSITIVE LOGITS
    åıĬåħ¶
    0.12
    duto
    0.07
    ubat
    0.07
    acha
    0.07
     INCLUDING
    0.07
     OTHERWISE
    0.07
     ÙĪÙħا
    0.07
    udad
    0.07
    afil
    0.07
    isas
    0.07
    Activations Density 0.041%

    No Known Activations