© 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. 88919
    Prev
    Next
    INDEX
    Explanations

    locations and amenities in a specific area

    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
    ja
    -0.07
    borough
    -0.06
    111
    -0.06
    Ø´ÙĨ
    -0.06
    õi
    -0.06
    ieme
    -0.06
    upe
    -0.06
     minded
    -0.06
    iry
    -0.06
    ÂŃi
    -0.06
    POSITIVE LOGITS
    åĨĨ
    0.07
     immediate
    0.07
    'gc
    0.06
     nearby
    0.06
     Protective
    0.06
     dint
    0.06
    á»ĵi
    0.06
     å¾ĴæŃ©
    0.06
     Jag
    0.06
    ../../
    0.05
    Activations Density 0.017%

    No Known Activations