© 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. 90382
    Prev
    Next
    INDEX
    Explanations

    references to political systems and ideologies, particularly pertaining to conservatism

    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
    zin
    -0.06
    zia
    -0.06
    enco
    -0.06
    ylon
    -0.06
     roman
    -0.06
    ænd
    -0.06
    abit
    -0.06
     danmark
    -0.06
    acom
    -0.06
    _sessions
    -0.06
    POSITIVE LOGITS
     McCart
    0.07
    abolic
    0.07
    ategy
    0.07
     ëĤĺ
    0.07
    unate
    0.06
    afari
    0.06
    enticator
    0.06
     å¸
    0.06
    198
    0.06
    ritis
    0.06
    Activations Density 0.001%

    No Known Activations