© 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. 89933
    Prev
    Next
    INDEX
    Explanations

    references to health-related topics and cultural significance

    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
    ugg
    -0.06
    qu
    -0.06
     behalf
    -0.06
    IODevice
    -0.05
    aki
    -0.05
     Dir
    -0.05
     removeObject
    -0.05
     tear
    -0.05
    amo
    -0.05
     affected
    -0.05
    POSITIVE LOGITS
    Qualifier
    0.07
    _misc
    0.07
    hled
    0.07
    QualifiedName
    0.07
    ombat
    0.07
    rete
    0.07
    HashCode
    0.07
    maal
    0.07
    ADDE
    0.07
    TEE
    0.07
    Activations Density 0.027%

    No Known Activations