© 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. 71377
    Prev
    Next
    INDEX
    Explanations

    activisms related to independence and anti-colonial movements

    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
    ninger
    -0.06
    amedi
    -0.06
     chill
    -0.06
     Globals
    -0.06
     xhttp
    -0.06
    razil
    -0.06
    esan
    -0.06
     reint
    -0.06
    apid
    -0.06
     zaw
    -0.06
    POSITIVE LOGITS
     independence
    0.14
     freedom
    0.13
     Independence
    0.12
     Freedom
    0.11
     liberation
    0.11
     freeing
    0.11
    Independ
    0.10
    Freedom
    0.10
     emanc
    0.10
     Liberation
    0.10
    Activations Density 0.091%

    No Known Activations