© 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. 15-LLAMASCOPE-RES-131K
    11. 90125
    Prev
    Next
    INDEX
    Explanations

    terms related to challenges or warnings associated with risky behaviors

    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
    Wunused
    -0.07
    ableView
    -0.07
    assis
    -0.06
    gor
    -0.06
     fontStyle
    -0.06
    çĴ°
    -0.06
    inyin
    -0.06
    deer
    -0.06
     remar
    -0.06
     iceberg
    -0.06
    POSITIVE LOGITS
     pus
    0.07
    ouver
    0.07
    ë²
    0.06
    airo
    0.06
    jest
    0.06
    лаÑĪ
    0.06
     Hatch
    0.06
    zept
    0.06
     Rust
    0.06
     Pillow
    0.06
    Activations Density 0.000%

    No Known Activations