© 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. 82143
    Prev
    Next
    INDEX
    Explanations

    instances of the word "beam" and its related forms in various contexts

    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
    ãģªãģĦ
    -0.08
    ais
    -0.08
    klä
    -0.07
    er
    -0.07
    arpa
    -0.07
    esi
    -0.07
    pard
    -0.07
    åĬŀæ³ķ
    -0.07
    reno
    -0.07
    iating
    -0.06
    POSITIVE LOGITS
    forming
    0.10
    former
    0.08
    stalk
    0.07
    ault
    0.07
     splitter
    0.07
    ibal
    0.07
    ERGY
    0.07
    croft
    0.07
    ibold
    0.07
    side
    0.07
    Activations Density 0.012%

    No Known Activations