© 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. 82936
    Prev
    Next
    INDEX
    Explanations

    phrases related to political discourse and leadership challenges

    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
    еÑģÑĤи
    -0.08
    alis
    -0.07
    aru
    -0.06
    incare
    -0.06
    emale
    -0.06
     vid
    -0.06
    onta
    -0.06
    enou
    -0.06
    ehir
    -0.06
    beit
    -0.06
    POSITIVE LOGITS
     whose
    0.09
     who
    0.08
    whose
    0.08
     someone
    0.07
    who
    0.07
    .Dispatcher
    0.07
    LLL
    0.07
    ibo
    0.06
     guy
    0.06
    ponsible
    0.06
    Activations Density 0.027%

    No Known Activations