© 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 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. 76423
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "going to," often associated with future actions or intentions

    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
    lo
    -0.08
    chn
    -0.07
    lep
    -0.06
    anya
    -0.06
    igkeit
    -0.06
    abr
    -0.06
     alınan
    -0.06
    à¸Ħ
    -0.06
    ogn
    -0.06
    ada
    -0.06
    POSITIVE LOGITS
    owler
    0.07
    ocket
    0.07
    ispers
    0.07
    kou
    0.07
    iams
    0.06
    ingham
    0.06
    ellipsis
    0.06
     guess
    0.06
    wort
    0.06
    strstr
    0.06
    Activations Density 0.012%

    No Known Activations