© 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. 71711
    Prev
    Next
    INDEX
    Explanations

    words related to the act of restarting or continuing activities or processes

    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
    ness
    -0.07
    red
    -0.07
    outh
    -0.07
    away
    -0.07
    ERM
    -0.06
    лÑİд
    -0.06
    isma
    -0.06
     Away
    -0.06
    rea
    -0.06
    ź
    -0.06
    POSITIVE LOGITS
     acquaintance
    0.08
    aurant
    0.08
     normal
    0.07
    /res
    0.07
    ķìĿ¸
    0.07
    .normalized
    0.06
    igsaw
    0.06
     activities
    0.06
    иболее
    0.06
    /start
    0.06
    Activations Density 0.004%

    No Known Activations