© 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. 404
    Prev
    Next
    INDEX
    Explanations

    terms related to governance and societal control mechanisms

    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
    557
    -0.07
    ahun
    -0.07
     Hindered
    -0.07
    je
    -0.06
    APPED
    -0.06
    lias
    -0.06
     graceful
    -0.06
    ÅĻád
    -0.06
    uhe
    -0.06
    indered
    -0.06
    POSITIVE LOGITS
    iola
    0.08
    istar
    0.07
    .scalar
    0.06
     rewrite
    0.06
    enever
    0.06
    afort
    0.06
     conforme
    0.06
    оÑģÑĤи
    0.06
    ominator
    0.06
    .@
    0.06
    Activations Density 0.027%

    No Known Activations