© 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. 56906
    Prev
    Next
    INDEX
    Explanations

    reports of incidents involving violence or crime

    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
    holm
    -0.07
    ä½IJ
    -0.07
    ذر
    -0.07
    æ´¥
    -0.07
    سر
    -0.06
     captivity
    -0.06
     chy
    -0.06
    .jd
    -0.06
     Webcam
    -0.06
     Kes
    -0.06
    POSITIVE LOGITS
     gang
    0.08
     bullet
    0.08
     hit
    0.06
     bra
    0.06
     car
    0.06
     turf
    0.06
    ÑĤии
    0.06
     emanc
    0.06
     hits
    0.06
    avia
    0.06
    Activations Density 0.040%

    No Known Activations