© 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. 94109
    Prev
    Next
    INDEX
    Explanations

    references to warnings or concerns about the dangers of artificial intelligence

    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
    (æ°´
    -0.08
    (åľŁ
    -0.07
    iasi
    -0.07
     Bless
    -0.07
    eing
    -0.07
     Gram
    -0.06
     Ùħاد
    -0.06
    ãĥ«ãĥķ
    -0.06
    amura
    -0.06
    enko
    -0.06
    POSITIVE LOGITS
     Haw
    0.07
     ENABLE
    0.07
     science
    0.06
     world
    0.06
    ãĥªãĥ³
    0.06
    aben
    0.06
     probes
    0.06
     BBC
    0.06
     Kerr
    0.06
     Tubes
    0.06
    Activations Density 0.001%

    No Known Activations