© 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. 76384
    Prev
    Next
    INDEX
    Explanations

    concepts related to recognition and legitimacy, particularly in a political or social context

    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
    #echo
    -0.07
     Andrews
    -0.07
    ewater
    -0.07
     dÆ°
    -0.07
    mey
    -0.07
    endar
    -0.07
    hardt
    -0.07
    lá
    -0.07
    жа
    -0.07
    INGTON
    -0.07
    POSITIVE LOGITS
     fait
    0.07
     authority
    0.07
     valid
    0.07
     Baum
    0.06
    fait
    0.06
    -valid
    0.06
     validity
    0.06
    iddle
    0.06
    realloc
    0.06
     legitimacy
    0.06
    Activations Density 0.015%

    No Known Activations