© 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. 17-LLAMASCOPE-RES-131K
    11. 76873
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize cultural pride and historical significance

    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
    Ã
    -0.07
     zastav
    -0.06
    clist
    -0.06
    ibo
    -0.06
    Bubble
    -0.06
    åĿĬ
    -0.06
    eca
    -0.06
    prm
    -0.06
    ä»Ģ
    -0.06
    marshall
    -0.06
    POSITIVE LOGITS
     leadership
    0.07
     consolid
    0.06
    ariant
    0.06
    agus
    0.06
    spo
    0.06
     Leadership
    0.06
    assi
    0.06
    uppen
    0.05
    late
    0.05
    ume
    0.05
    Activations Density 0.009%

    No Known Activations