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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 70198
    Prev
    Next
    INDEX
    Explanations

    the word "along" in various 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
    važ
    -0.07
    ãģªãģĬ
    -0.06
    ashtra
    -0.06
    ymb
    -0.06
    ple
    -0.06
    kova
    -0.06
    idal
    -0.06
    rif
    -0.06
    zelf
    -0.06
    ocks
    -0.06
    POSITIVE LOGITS
     with
    0.09
     others
    0.08
     vỼi
    0.08
    ãĤĪãģ³
    0.08
     other
    0.08
    along
    0.07
    with
    0.07
    heiro
    0.07
     along
    0.07
     avec
    0.07
    Activations Density 0.011%

    No Known Activations