© 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. 78401
    Prev
    Next
    INDEX
    Explanations

    infinitive verbs and the concept of learning or aspirational actions

    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
    riba
    -0.07
    cly
    -0.07
    at
    -0.07
    ixin
    -0.06
    lava
    -0.06
    меÑĤÑĮ
    -0.06
     Sunderland
    -0.06
    undai
    -0.06
    anca
    -0.06
    ignet
    -0.06
    POSITIVE LOGITS
    rops
    0.07
    recogn
    0.06
    skills
    0.06
    yasal
    0.06
     Skills
    0.06
     skills
    0.06
    tol
    0.06
    olerance
    0.06
     opendir
    0.06
    avigate
    0.06
    Activations Density 0.012%

    No Known Activations