© 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. 41007
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax and constructs

    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
    amd
    -0.06
    _IMPL
    -0.06
    atrice
    -0.06
     kem
    -0.06
    AREA
    -0.06
    .Assembly
    -0.06
    .crm
    -0.06
    .DropDown
    -0.06
    _qs
    -0.06
    otime
    -0.06
    POSITIVE LOGITS
     each
    0.18
    each
    0.16
    Each
    0.15
     Each
    0.14
     chaque
    0.13
     EACH
    0.12
    .each
    0.12
    _each
    0.12
     каждÑĭй
    0.12
     cada
    0.12
    Activations Density 0.113%

    No Known Activations