© 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. 71556
    Prev
    Next
    INDEX
    Explanations

    statements about political opinions and shifts

    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
    urette
    -0.10
    angan
    -0.09
    延
    -0.09
    peq
    -0.09
    ospace
    -0.08
    ofday
    -0.08
    nnen
    -0.08
    viÄį
    -0.08
    oleon
    -0.08
    odyn
    -0.08
    POSITIVE LOGITS
     change
    0.11
     changed
    0.10
     transformation
    0.10
     changes
    0.09
     now
    0.09
     shift
    0.08
    Changed
    0.08
     suddenly
    0.08
     Change
    0.08
     reversal
    0.08
    Activations Density 0.057%

    No Known Activations