© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 57146
    Prev
    Next
    INDEX
    Explanations

    references to online shopping or stores

    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
    igg
    -0.07
    ael
    -0.07
    ÙĤع
    -0.06
    -0.06
    ews
    -0.06
    initializer
    -0.06
    iosper
    -0.06
    iginal
    -0.06
    andre
    -0.06
    ylim
    -0.06
    POSITIVE LOGITS
    rias
    0.08
    ér
    0.07
     Fahr
    0.07
    etim
    0.07
    _graphics
    0.07
    foon
    0.07
    nds
    0.06
    isci
    0.06
    aise
    0.06
    itur
    0.06
    Activations Density 0.000%

    No Known Activations