© 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. 125411
    Prev
    Next
    INDEX
    Explanations

    references to public opinion on political issues and concerns

    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
    avana
    -0.09
    otal
    -0.08
    entai
    -0.08
    çŁ¢
    -0.07
    зÑĭ
    -0.07
    ctest
    -0.07
    orting
    -0.07
    098
    -0.07
    acci
    -0.07
    thal
    -0.07
    POSITIVE LOGITS
     overall
    0.07
    m
    0.06
    ember
    0.06
     job
    0.06
    overall
    0.06
    Overall
    0.06
     Overall
    0.06
    un
    0.06
    w
    0.06
     direction
    0.06
    Activations Density 0.010%

    No Known Activations