© 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 EvalsExportsAPI 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. 71299
    Prev
    Next
    INDEX
    Explanations

    references to specific locations or demographic mentions within a political context

    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
    okus
    -0.07
    reon
    -0.07
     CHARSET
    -0.07
    endors
    -0.07
    acci
    -0.07
    ystone
    -0.07
    gaard
    -0.07
    icator
    -0.07
    igor
    -0.07
    istrat
    -0.07
    POSITIVE LOGITS
    .defer
    0.07
     parts
    0.07
     Parts
    0.06
     Jin
    0.06
     Chung
    0.06
    velle
    0.06
     Wi
    0.05
    ANS
    0.05
     Pit
    0.05
     fix
    0.05
    Activations Density 0.017%

    No Known Activations