© 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. 15-LLAMASCOPE-RES-131K
    11. 87899
    Prev
    Next
    INDEX
    Explanations

    references to incarceration and systemic injustice

    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
    SUMER
    -0.07
    ARRIER
    -0.07
    )did
    -0.07
     Barrier
    -0.06
     multiline
    -0.06
     NEGLIGENCE
    -0.06
    vit
    -0.06
    æŃ
    -0.06
    ereg
    -0.06
     prosecution
    -0.06
    POSITIVE LOGITS
    ç¯ī
    0.07
     overcrow
    0.06
    ock
    0.06
     à¸Īำ
    0.06
    edn
    0.06
    esign
    0.06
    243
    0.06
     capacity
    0.06
    å·»
    0.06
     IPS
    0.06
    Activations Density 0.021%

    No Known Activations