© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 90736
    Prev
    Next
    INDEX
    Explanations

    references to organizations and corporate entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Major company and brand names appearing in business news, corporate announcements, and commercial contexts.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    -American
    -0.06
    á»ķi
    -0.06
    odes
    -0.06
     Bes
    -0.06
     gas
    -0.05
    ordova
    -0.05
    rell
    -0.05
     Armour
    -0.05
    ordo
    -0.05
     abs
    -0.05
    POSITIVE LOGITS
     Europe
    0.09
     UK
    0.07
     localize
    0.07
     lô
    0.07
     Shut
    0.07
    ABCDEFGHIJKLMNOP
    0.07
    -CN
    0.07
     ÐļÑĢа
    0.07
    ÙĦÙħاÙĨ
    0.07
    Refs
    0.07
    Activations Density 0.046%

    No Known Activations