© 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. 70757
    Prev
    Next
    INDEX
    Explanations

    words related to fitting or accommodating needs and preferences

    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
    705
    -0.07
    h
    -0.06
     fract
    -0.06
    beb
    -0.06
    eu
    -0.06
    aps
    -0.06
    hti
    -0.06
    nist
    -0.06
    Æ
    -0.06
    APS
    -0.06
    POSITIVE LOGITS
    ably
    0.11
     purposes
    0.08
     Ñģобой
    0.08
    'gc
    0.07
    oured
    0.07
    ively
    0.07
    astos
    0.07
    -prepend
    0.07
    CurrentValue
    0.07
    ango
    0.07
    Activations Density 0.004%

    No Known Activations