© 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. 129162
    Prev
    Next
    INDEX
    Explanations

    references to government programs and initiatives addressing crime and security issues

    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
    linger
    -0.07
    uling
    -0.06
    orde
    -0.06
    anzi
    -0.06
    AMPL
    -0.06
     hereby
    -0.06
    allet
    -0.06
     etc
    -0.06
     —
    -0.06
    egra
    -0.06
    POSITIVE LOGITS
    ecd
    0.07
    enor
    0.06
     gener
    0.06
     anecd
    0.06
    HasKey
    0.06
    Additionally
    0.06
     esp
    0.06
     ElementType
    0.06
    esk
    0.06
    unicode
    0.06
    Activations Density 0.034%

    No Known Activations