© 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. 60852
    Prev
    Next
    INDEX
    Explanations

    discussions emphasizing the concept of reality, often in multiple contexts or perspectives

    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
    orado
    -0.09
     trÆ°á»Łng
    -0.08
    mant
    -0.08
    annon
    -0.08
    Çİ
    -0.07
    erman
    -0.07
    ery
    -0.07
    mor
    -0.07
    ded
    -0.07
    esian
    -0.07
    POSITIVE LOGITS
    tainment
    0.07
    108
    0.07
    inus
    0.07
    eum
    0.06
    itä
    0.06
    iable
    0.06
    ìĤ¬íķŃ
    0.06
    797
    0.06
    ocrine
    0.06
    -facing
    0.06
    Activations Density 0.009%

    No Known Activations