© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 105044
    Prev
    Next
    INDEX
    Explanations

    prepositions and conjunctions indicating relationships or conditions

    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
    ossip
    -0.08
    emit
    -0.07
    zin
    -0.07
    lava
    -0.07
    hread
    -0.07
    unga
    -0.06
    emax
    -0.06
    istory
    -0.06
    itel
    -0.06
    atatype
    -0.06
    POSITIVE LOGITS
    otti
    0.07
    abi
    0.06
    oli
    0.06
    cre
    0.06
     dök
    0.06
     Ekon
    0.06
     PTR
    0.06
     Pemb
    0.06
    اساÙĨ
    0.06
    ger
    0.05
    Activations Density 0.001%

    No Known Activations