Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 40521
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate interconnectedness within communities

    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
    -0.08
     èĩªåĬ¨çĶŁæĪIJ
    -0.07
    oste
    -0.07
    éĹ»
    -0.07
    vie
    -0.07
    окÑģи
    -0.07
    esen
    -0.07
    esteem
    -0.07
    aris
    -0.07
    ÑĢава
    -0.07
    POSITIVE LOGITS
     people
    0.07
     individuals
    0.07
    lic
    0.07
    uba
    0.07
    yled
    0.06
     lik
    0.06
     active
    0.06
    cca
    0.06
    people
    0.06
     similarly
    0.06
    Activations Density 0.022%

    No Known Activations