© 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. 15-LLAMASCOPE-RES-131K
    11. 760
    Prev
    Next
    INDEX
    Explanations

    references to systemic issues and failures in societal structures

    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
    utsch
    -0.08
    anje
    -0.07
    otto
    -0.07
    adem
    -0.07
    stamp
    -0.06
    setName
    -0.06
    cott
    -0.06
    ussy
    -0.06
    MG
    -0.06
    ORAGE
    -0.06
    POSITIVE LOGITS
     community
    0.06
     importance
    0.06
     previously
    0.06
     Importance
    0.06
     existing
    0.06
    need
    0.06
     Need
    0.06
     need
    0.06
    ueue
    0.06
    åİŁæĿ¥
    0.06
    Activations Density 0.016%

    No Known Activations