© 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 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. 88399
    Prev
    Next
    INDEX
    Explanations

    terms related to ancestry and heritage

    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
    lessly
    -0.10
    ardy
    -0.08
    fully
    -0.08
    halb
    -0.08
    etheless
    -0.07
    ำ
    -0.07
    lio
    -0.07
    mediately
    -0.07
    scribe
    -0.06
    tracts
    -0.06
    POSITIVE LOGITS
    ä»Ģ
    0.07
    .paging
    0.07
     quoi
    0.07
    ัวร
    0.07
    _taxonomy
    0.06
     VÅ¡ech
    0.06
    ddl
    0.06
    ancial
    0.06
    eniable
    0.06
    ness
    0.06
    Activations Density 0.027%

    No Known Activations