© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 126738
    Prev
    Next
    INDEX
    Explanations

    mentions of destruction and its aftermath in vulnerable environments

    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
    sdale
    -0.06
    essel
    -0.06
    reich
    -0.06
    åĪ»
    -0.06
     reversible
    -0.06
    esi
    -0.06
    heels
    -0.06
    Ðİ
    -0.06
    etch
    -0.06
    oi
    -0.06
    POSITIVE LOGITS
     Levy
    0.06
    loyd
    0.06
    apor
    0.06
     entr
    0.06
     overnight
    0.06
    mailbox
    0.06
    alama
    0.06
     ÎijÏĢο
    0.06
    yd
    0.06
     debris
    0.06
    Activations Density 0.008%

    No Known Activations