© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 119184
    Prev
    Next
    INDEX
    Explanations

    references to political positions and committee roles

    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
     mdi
    -0.08
    bsolute
    -0.08
    jeme
    -0.07
    ackson
    -0.07
    ãģıãĤĵ
    -0.07
    baugh
    -0.07
    _crop
    -0.07
    igner
    -0.07
     Delegate
    -0.06
    iliz
    -0.06
    POSITIVE LOGITS
     Committee
    0.08
     House
    0.08
     sub
    0.07
     committee
    0.07
     smarty
    0.07
     jurisdiction
    0.07
    uc
    0.07
     Subcommittee
    0.07
    ascus
    0.07
    ollar
    0.06
    Activations Density 0.009%

    No Known Activations