© 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. 15277
    Prev
    Next
    INDEX
    Explanations

    data related to statistics and demographics over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Word fragments that form parts of Spanish vocabulary, particularly segments of verbs, nouns and adjectives that are essential to constructing meaning in Spanish text.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    Atual
    -0.08
     jog
    -0.07
     jogo
    -0.07
     Rio
    -0.07
     Pessoa
    -0.06
    Telefone
    -0.06
    626
    -0.06
    ário
    -0.06
     Brazilian
    -0.06
    _nome
    -0.06
    POSITIVE LOGITS
    иденÑĤ
    0.08
    ίγ
    0.07
    ιθ
    0.07
    isÃŃ
    0.07
    agues
    0.07
    Cancelable
    0.07
    anes
    0.07
    икÑĥ
    0.07
    aped
    0.07
    ovÃŃ
    0.07
    Activations Density 0.357%

    No Known Activations