© 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. 73763
    Prev
    Next
    INDEX
    Explanations

    references to North Korea and its leadership

    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
    anova
    -0.06
    bedo
    -0.06
    784
    -0.06
    ritch
    -0.06
    Occ
    -0.06
    iat
    -0.06
    erate
    -0.06
    -bodied
    -0.06
    lice
    -0.06
    737
    -0.06
    POSITIVE LOGITS
    ophil
    0.07
    /interfaces
    0.07
    ãĤ¦ãĤ¹
    0.07
    æijĺ
    0.06
    ÅĻi
    0.06
    chwitz
    0.06
    edn
    0.06
    appiness
    0.06
    inders
    0.06
    (Unknown
    0.06
    Activations Density 0.008%

    No Known Activations