© 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. 55251
    Prev
    Next
    INDEX
    Explanations

    phrases associated with calling or naming things

    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
    &action
    -0.07
    INGLE
    -0.06
    ìĻ
    -0.06
    alc
    -0.06
    .synthetic
    -0.06
    .isOpen
    -0.06
    EventData
    -0.06
    aroo
    -0.06
    SSIP
    -0.06
    _EVAL
    -0.06
    POSITIVE LOGITS
    åIJ§
    0.09
    aki
    0.07
    UBL
    0.06
     officially
    0.06
    ajor
    0.06
    ernen
    0.06
     whatever
    0.06
    chalk
    0.06
     anytime
    0.06
     impressed
    0.06
    Activations Density 0.010%

    No Known Activations