© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 119444
    Prev
    Next
    INDEX
    Explanations

    content related to explicit sexual themes and activities involving minors

    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
     luder
    -0.06
    ç°
    -0.06
    astr
    -0.06
     Son
    -0.06
     Prostit
    -0.06
     Beard
    -0.06
    rane
    -0.06
     trem
    -0.06
    PointCloud
    -0.06
    eprom
    -0.05
    POSITIVE LOGITS
     ArrayBuffer
    0.07
    iface
    0.07
     solic
    0.07
    udos
    0.07
     explicit
    0.06
     editorial
    0.06
    ifax
    0.06
    Explicit
    0.06
    Lit
    0.06
    ife
    0.06
    Activations Density 0.007%

    No Known Activations