© 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. 78288
    Prev
    Next
    INDEX
    Explanations

    specific mentions of DNA and its properties

    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
     compound
    -0.07
    Compound
    -0.07
    compound
    -0.07
    pmat
    -0.06
    oui
    -0.06
    GetInstance
    -0.06
     Integral
    -0.06
    roti
    -0.06
    otime
    -0.06
    Ä±ÅŁÄ±k
    -0.06
    POSITIVE LOGITS
    -template
    0.08
     template
    0.07
    endale
    0.07
     hel
    0.07
     Lawn
    0.06
    _acquire
    0.06
    Bubble
    0.06
     Econ
    0.06
     Templates
    0.06
     templates
    0.06
    Activations Density 0.018%

    No Known Activations