© 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. 59892
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "pick up" and related 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
    arget
    -0.07
    olia
    -0.07
    irie
    -0.07
    ing
    -0.06
    mj
    -0.06
    ingt
    -0.06
    uts
    -0.06
    ted
    -0.06
    ledge
    -0.06
    æĬľ
    -0.06
    POSITIVE LOGITS
     Pace
    0.09
    .pick
    0.09
     pace
    0.09
     slack
    0.07
    pick
    0.07
    _THROW
    0.07
    raig
    0.07
    æ¢
    0.07
    picked
    0.07
     picks
    0.07
    Activations Density 0.012%

    No Known Activations