© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 2952
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing the concept of "most" as a qualifier indicating prevalence or majority

    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
     sake
    -0.07
    adius
    -0.06
    akov
    -0.06
    aid
    -0.06
    ught
    -0.06
    ong
    -0.06
    igs
    -0.06
    ries
    -0.05
    aeper
    -0.05
    onium
    -0.05
    POSITIVE LOGITS
     importantly
    0.09
    RTOS
    0.08
    Č↵
    0.07
     Rao
    0.07
    afa
    0.07
    maj
    0.07
    лаж
    0.07
    иболее
    0.07
    isches
    0.07
     likely
    0.06
    Activations Density 0.016%

    No Known Activations