© 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. 125326
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically names of individuals and organizations

    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
    iye
    -0.07
    lio
    -0.07
    Č↵
    -0.07
    £i
    -0.07
    лев
    -0.06
    igua
    -0.06
    опÑĢоÑģ
    -0.06
    kish
    -0.06
    theless
    -0.06
    .water
    -0.06
    POSITIVE LOGITS
    495
    0.06
     when
    0.06
     echoing
    0.06
    605
    0.06
    859
    0.06
    erras
    0.06
    503
    0.06
    403
    0.06
     Mason
    0.06
     atIndex
    0.06
    Activations Density 0.028%

    No Known Activations