© 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. 107287
    Prev
    Next
    INDEX
    Explanations

    clusters of the word "in" within various contexts related to location or inclusion

    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
    etto
    -0.07
     firstly
    -0.07
     either
    -0.07
    adays
    -0.07
    istan
    -0.07
    stag
    -0.06
    ongs
    -0.06
     Firstly
    -0.06
    ensen
    -0.06
    owie
    -0.06
    POSITIVE LOGITS
    /or
    0.11
    /OR
    0.09
     therefore
    0.09
    rogen
    0.08
    eut
    0.08
     importantly
    0.08
    erken
    0.07
    itti
    0.07
     subsequently
    0.07
     thereby
    0.07
    Activations Density 0.050%

    No Known Activations