© 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. 84616
    Prev
    Next
    INDEX
    Explanations

    instances of ordinal phrases or references to being the first in a sequence

    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
    aton
    -0.06
    ÙĥÙĪÙĨ
    -0.06
    .performance
    -0.06
    CCCCCC
    -0.06
    åºŃ
    -0.06
    LCD
    -0.06
    ilst
    -0.06
    .Expect
    -0.06
    alta
    -0.06
    &o
    -0.06
    POSITIVE LOGITS
     tiên
    0.08
    opsis
    0.08
    ests
    0.08
    orro
    0.07
    æį·
    0.07
    iesen
    0.07
    efs
    0.06
    alaria
    0.06
    ascar
    0.06
    viron
    0.06
    Activations Density 0.011%

    No Known Activations