© 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. 15-LLAMASCOPE-RES-131K
    11. 89854
    Prev
    Next
    INDEX
    Explanations

    references to children and family-related themes

    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
    bach
    -0.07
    دÙĨ
    -0.07
    eph
    -0.07
    _rg
    -0.06
     Residential
    -0.06
    ANNOT
    -0.06
    ãĤ¤ãĥ³ãĥĪ
    -0.06
    aign
    -0.06
    obar
    -0.06
    lear
    -0.06
    POSITIVE LOGITS
    Paren
    0.07
    aje
    0.07
    atz
    0.07
     dil
    0.06
    573
    0.06
    ¹
    0.06
    thood
    0.06
    Ä°R
    0.06
     whom
    0.06
    rrha
    0.06
    Activations Density 0.022%

    No Known Activations