© 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. 40967
    Prev
    Next
    INDEX
    Explanations

    references to sibling dynamics and family 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
    ä¸ĸ
    -0.08
    .isSuccess
    -0.08
    AGMA
    -0.07
    rike
    -0.07
    @Id
    -0.07
    wine
    -0.07
    iode
    -0.07
     à¤ľà¤µ
    -0.07
    enou
    -0.07
    à¹ĥà¸Ī
    -0.07
    POSITIVE LOGITS
     Salvador
    0.06
     already
    0.06
     nich
    0.06
    hin
    0.06
    ipay
    0.06
     pre
    0.05
    igrams
    0.05
     Already
    0.05
     Adjust
    0.05
    ipi
    0.05
    Activations Density 0.019%

    No Known Activations