© 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. 119684
    Prev
    Next
    INDEX
    Explanations

    words related to chewing or chewable items

    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
    -China
    -0.09
     charged
    -0.08
    channel
    -0.07
    tü
    -0.07
    廳
    -0.07
    ãĤĥ
    -0.07
    ej
    -0.07
    annel
    -0.07
    ottage
    -0.07
    eve
    -0.07
    POSITIVE LOGITS
    lain
    0.10
    soever
    0.08
    strap
    0.08
    anooga
    0.07
    sterol
    0.07
    abort
    0.07
    ilde
    0.07
    оÑĥ
    0.07
    Mate
    0.07
    wick
    0.07
    Activations Density 0.046%

    No Known Activations