© 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. 4280
    Prev
    Next
    INDEX
    Explanations

    terms related to the effectiveness of treatments or interventions

    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
    arden
    -0.07
     ÙħØ«
    -0.07
    QUIRES
    -0.07
    jit
    -0.07
    taire
    -0.07
    iership
    -0.06
    linger
    -0.06
    asser
    -0.06
    akers
    -0.06
    OUCH
    -0.06
    POSITIVE LOGITS
     regarding
    0.09
     against
    0.08
    à¹ĥà¸Ļà¸ģาร
    0.08
    Against
    0.07
    ummings
    0.07
    ForObject
    0.07
     meeting
    0.07
     Against
    0.07
    pek
    0.07
    shan
    0.07
    Activations Density 0.041%

    No Known Activations