© 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. 40025
    Prev
    Next
    INDEX
    Explanations

    details related to governmental actions and initiatives

    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
    inati
    -0.06
    ãĥ¯ãĤ¤ãĥĪ
    -0.06
    ги
    -0.06
     kia
    -0.06
    å±±å¸Ĥ
    -0.06
    agina
    -0.06
    bern
    -0.06
    æ³Ľ
    -0.06
    cae
    -0.06
    observeOn
    -0.06
    POSITIVE LOGITS
     similarly
    0.16
     theirs
    0.13
     ebenfalls
    0.13
     similar
    0.12
     likewise
    0.11
     ÑĤоже
    0.11
    similar
    0.11
     Similarly
    0.10
    Similarly
    0.10
    imilar
    0.09
    Activations Density 0.061%

    No Known Activations