© 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. 61792
    Prev
    Next
    INDEX
    Explanations

    specific references to legal codes and case law

    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
    y
    -0.07
    ing
    -0.07
     subs
    -0.06
    iffin
    -0.06
    acking
    -0.06
    -
    -0.06
    ër
    -0.06
    iddles
    -0.06
    a
    -0.05
    iff
    -0.05
    POSITIVE LOGITS
    	freopen
    0.08
    -alist
    0.08
    оÑĢаÑı
    0.08
    _clr
    0.07
    nech
    0.07
    noch
    0.07
    надлеж
    0.07
    ValuePair
    0.07
    .foundation
    0.07
    spender
    0.07
    Activations Density 0.001%

    No Known Activations