© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 27658
    Prev
    Next
    INDEX
    Explanations

    mentions of political processes and leadership 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
     âĹĦ
    -0.08
    eniable
    -0.08
    isque
    -0.08
    ARCHAR
    -0.07
    ettes
    -0.07
    lund
    -0.07
    oki
    -0.07
    artner
    -0.07
    sumer
    -0.07
    ziej
    -0.07
    POSITIVE LOGITS
     votes
    0.09
     voting
    0.07
     vote
    0.07
     Candid
    0.07
     proxies
    0.07
     abst
    0.06
     secret
    0.06
     outcome
    0.06
     rank
    0.06
     rounds
    0.06
    Activations Density 0.016%

    No Known Activations