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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 90330
    Prev
    Next
    INDEX
    Explanations

    references to individuals and legal definitions related to entities and relationships

    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
    meni
    -0.09
    اÙĦÙĬا
    -0.08
    аÑĢÑĩ
    -0.08
    zung
    -0.08
    ovÃŃ
    -0.08
     torino
    -0.08
    usan
    -0.08
    urnished
    -0.08
    оби
    -0.08
    иÑĢа
    -0.07
    POSITIVE LOGITS
     who
    0.06
    aho
    0.06
     k
    0.06
    eres
    0.06
     outside
    0.05
    208
    0.05
    207
    0.05
     Giuliani
    0.05
     reliably
    0.05
     whom
    0.05
    Activations Density 0.017%

    No Known Activations