© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 55519
    Prev
    Next
    INDEX
    Explanations

    prepositions and phrases indicating location or time

    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
     itself
    -0.07
     п
    -0.06
    inyin
    -0.06
    odon
    -0.06
    alette
    -0.06
    kla
    -0.06
     yourself
    -0.06
    uyo
    -0.06
     kepada
    -0.06
    ilan
    -0.06
    POSITIVE LOGITS
     whom
    0.08
    çĵľ
    0.07
    ForResult
    0.06
    _$_
    0.06
     Ulus
    0.06
    herits
    0.06
    aggi
    0.06
    eyin
    0.06
     mutual
    0.06
    BILE
    0.06
    Activations Density 0.051%

    No Known Activations