© 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. 119686
    Prev
    Next
    INDEX
    Explanations

    terms related to global or widespread significance

    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
    soever
    -0.08
    jie
    -0.08
     Credential
    -0.07
    ãģįãģŁ
    -0.07
    work
    -0.07
     Jenner
    -0.07
    anti
    -0.07
    role
    -0.07
    locker
    -0.06
    related
    -0.06
    POSITIVE LOGITS
    /global
    0.09
    -reaching
    0.07
    /int
    0.07
    edition
    0.07
    /down
    0.07
    /reg
    0.07
    /local
    0.07
    ToLocal
    0.07
    ed
    0.06
    475
    0.06
    Activations Density 0.010%

    No Known Activations