© 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. 75244
    Prev
    Next
    INDEX
    Explanations

    terms that signify standards or norms in various contexts

    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
     Luz
    -0.06
    aggio
    -0.06
    essel
    -0.06
    abb
    -0.05
     Remed
    -0.05
    clinic
    -0.05
    omain
    -0.05
    anno
    -0.05
     can
    -0.05
    olio
    -0.05
    POSITIVE LOGITS
    efault
    0.08
     increasingly
    0.08
    norm
    0.08
    /default
    0.07
     choice
    0.07
     ÑĢазм
    0.07
    entina
    0.07
    Choice
    0.07
     accepted
    0.07
    _choice
    0.07
    Activations Density 0.025%

    No Known Activations