© 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. 9-LLAMASCOPE-RES-131K
    11. 96532
    Prev
    Next
    INDEX
    Explanations

    references to various types of tape and their uses

    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
    zek
    -0.07
    rie
    -0.07
    /goto
    -0.07
    roi
    -0.06
    bies
    -0.06
    readcr
    -0.06
    ried
    -0.06
    ollapse
    -0.06
    li
    -0.06
    zed
    -0.06
    POSITIVE LOGITS
    stry
    0.09
    adium
    0.08
    uen
    0.08
    -record
    0.07
    /cards
    0.07
    ê´Ģ
    0.07
    faction
    0.07
    ãĥ£
    0.07
    azard
    0.07
    oleon
    0.07
    Activations Density 0.004%

    No Known Activations