© 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. 74471
    Prev
    Next
    INDEX
    Explanations

    mentions of locations and organizational entities

    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
    onto
    -0.07
    ¶Į
    -0.06
    mts
    -0.06
    òi
    -0.06
    åħĥ
    -0.06
    ÑıÑģÑĮ
    -0.06
    iks
    -0.06
    ubre
    -0.06
    ÂŃtion
    -0.06
    uffer
    -0.06
    POSITIVE LOGITS
    ollo
    0.07
    utas
    0.07
     Kup
    0.07
    ÑĥÑĢÑģ
    0.07
    aga
    0.07
     konkrét
    0.06
    åħ
    0.06
    vers
    0.06
    cept
    0.06
    sol
    0.06
    Activations Density 0.031%

    No Known Activations