© 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. 82244
    Prev
    Next
    INDEX
    Explanations

    instances of violence and aggression

    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
    ãģĻãĤĮãģ°
    -0.07
     alloc
    -0.07
    ìłľ
    -0.06
    agher
    -0.06
    akra
    -0.06
    uais
    -0.06
    ought
    -0.06
    å¼ķãģį
    -0.06
    .decor
    -0.06
    ÃŃda
    -0.06
    POSITIVE LOGITS
     either
    0.15
    either
    0.14
     sometimes
    0.13
     often
    0.12
    sometimes
    0.11
     Either
    0.11
    often
    0.10
     Sometimes
    0.10
    Either
    0.10
    ometimes
    0.10
    Activations Density 0.038%

    No Known Activations