© 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. 128554
    Prev
    Next
    INDEX
    Explanations

    terms related to protection and security measures

    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
    acher
    -0.07
    anka
    -0.07
    ighb
    -0.06
    лем
    -0.06
    isp
    -0.06
    ider
    -0.06
    lish
    -0.06
    quam
    -0.06
    esseract
    -0.06
    /graphql
    -0.06
    POSITIVE LOGITS
    ing
    0.09
    ed
    0.09
    edly
    0.08
    edBy
    0.07
     against
    0.07
    edn
    0.07
    /rest
    0.07
    à¥įध
    0.07
     Against
    0.07
    _ipc
    0.07
    Activations Density 0.002%

    No Known Activations