© 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. 95650
    Prev
    Next
    INDEX
    Explanations

    references to individuals and groups in the context of societal issues or events

    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
    á»ĵn
    -0.07
    uentes
    -0.07
    cie
    -0.07
    Ú¯ÙĪ
    -0.06
     pcm
    -0.06
     Preis
    -0.06
     Ekon
    -0.06
    PEG
    -0.06
    صÙĩ
    -0.06
    macı
    -0.06
    POSITIVE LOGITS
     died
    0.06
    åĮĸ
    0.06
     familiar
    0.06
    .ga
    0.05
    ?(:
    0.05
    å·ŀå¸Ĥ
    0.05
    ">ÃĹ</
    0.05
    ãĥ¼ãĥŃ
    0.05
    Browser
    0.05
    ulo
    0.05
    Activations Density 0.076%

    No Known Activations