© 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. 9-LLAMASCOPE-RES-131K
    11. 95893
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Wyoming" and related place names

    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
    ei
    -0.07
    riage
    -0.06
    ing
    -0.06
     Saras
    -0.06
    åłĤ
    -0.06
    eo
    -0.06
    iral
    -0.06
    adolu
    -0.06
    ting
    -0.06
     Tampa
    -0.05
    POSITIVE LOGITS
    urette
    0.08
    iland
    0.08
    defgroup
    0.07
    taÅŁ
    0.07
    ãĥ¼ãĤ¹
    0.07
    iferay
    0.07
    retweeted
    0.07
    áze
    0.07
    çĢ
    0.07
    Ñĩил
    0.06
    Activations Density 0.008%

    No Known Activations