© 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. 57580
    Prev
    Next
    INDEX
    Explanations

    phrases related to representation and advocacy on behalf of others

    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
    :async
    -0.07
    asu
    -0.07
    lech
    -0.07
    rema
    -0.07
    ÑĤÑİ
    -0.07
    jur
    -0.07
     ÄĮer
    -0.07
    warts
    -0.07
    usan
    -0.07
    ype
    -0.07
    POSITIVE LOGITS
     behalf
    0.21
     representing
    0.10
    代表
    0.09
     represent
    0.09
     represents
    0.08
     zastup
    0.08
     representation
    0.07
    represent
    0.07
     Represent
    0.07
     ëĮĢíijľ
    0.07
    Activations Density 0.028%

    No Known Activations