© 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. 29142
    Prev
    Next
    INDEX
    Explanations

    instances of the word "graduated" and related terms about educational achievements

    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
    INTR
    -0.07
    aleigh
    -0.06
    kins
    -0.06
    anship
    -0.06
    statt
    -0.06
    ington
    -0.06
    _PROTO
    -0.06
    ikel
    -0.06
    entic
    -0.06
    culture
    -0.06
    POSITIVE LOGITS
     zwar
    0.07
     fieldType
    0.07
    425
    0.07
    .press
    0.06
    PointerException
    0.06
    iglia
    0.06
    fromJson
    0.06
    UILTIN
    0.06
    builtin
    0.06
     ACK
    0.06
    Activations Density 0.006%

    No Known Activations