© 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. 17-LLAMASCOPE-RES-131K
    11. 85271
    Prev
    Next
    INDEX
    Explanations

    names of historical or political figures and their affiliations

    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
    estone
    -0.08
     Antar
    -0.07
    efon
    -0.07
    estroy
    -0.06
    \\.
    -0.06
    Äįer
    -0.06
    celik
    -0.06
     thy
    -0.06
    bish
    -0.06
    ãĥ©ãĤ¤ãĥĪ
    -0.06
    POSITIVE LOGITS
    ↵↵
    0.07
    æ
    0.06
    çıŃ
    0.06
    ÏĢλ
    0.06
    unken
    0.06
    suppress
    0.06
     Conc
    0.06
    alc
    0.06
    adu
    0.06
    IFE
    0.06
    Activations Density 0.139%

    No Known Activations