© 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. 85115
    Prev
    Next
    INDEX
    Explanations

    references to ancestry or lineage

    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
    841
    -0.06
    556
    -0.06
    .desktop
    -0.06
    inel
    -0.06
    796
    -0.06
    ä¸įäºĨ
    -0.06
    ils
    -0.06
    151
    -0.06
    969
    -0.06
     Dame
    -0.06
    POSITIVE LOGITS
    amble
    0.07
     dikke
    0.07
    anson
    0.07
    Binder
    0.06
    izont
    0.06
     prospective
    0.06
    аки
    0.06
    ür
    0.06
    .BorderColor
    0.06
    akra
    0.06
    Activations Density 0.022%

    No Known Activations