Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 106503
    Prev
    Next
    INDEX
    Explanations

    references to political structures or entities

    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
    ênh
    -0.08
    ellers
    -0.08
    باÙĨ
    -0.07
    hattan
    -0.07
    holds
    -0.07
    ertas
    -0.07
    alog
    -0.07
    ODE
    -0.07
    istrovstvÃŃ
    -0.07
    elling
    -0.07
    POSITIVE LOGITS
    akov
    0.07
     incorrect
    0.07
     economy
    0.07
    conomy
    0.07
     Economy
    0.07
    boro
    0.06
     Correct
    0.06
    prav
    0.06
    ELY
    0.06
    Ñģи
    0.06
    Activations Density 0.009%

    No Known Activations