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

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 62474
    Prev
    Next
    INDEX
    Explanations

    references to political maneuvers and power dynamics

    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
    Wunused
    -0.08
    kö
    -0.07
    /tos
    -0.07
    °}
    -0.07
    idunt
    -0.07
    allis
    -0.07
    arken
    -0.07
    oze
    -0.07
    ddl
    -0.07
    gom
    -0.06
    POSITIVE LOGITS
     remaining
    0.06
    lava
    0.06
    remaining
    0.06
    Ø·Ùĩ
    0.05
    ocos
    0.05
    irit
    0.05
    962
    0.05
     Bord
    0.05
    affected
    0.05
     currently
    0.05
    Activations Density 0.077%

    No Known Activations