© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 126783
    Prev
    Next
    INDEX
    Explanations

    the word "just" used in various contexts

    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
     Mey
    -0.07
    .mybatisplus
    -0.07
    addock
    -0.06
     buggy
    -0.06
    seys
    -0.06
    urdy
    -0.06
    (#)
    -0.06
    quire
    -0.06
    ulumi
    -0.06
    .hwp
    -0.06
    POSITIVE LOGITS
    illac
    0.07
     needed
    0.07
     Needed
    0.06
    лам
    0.06
    enda
    0.06
    ics
    0.06
     curves
    0.06
    artz
    0.06
     overhead
    0.06
    anken
    0.06
    Activations Density 0.016%

    No Known Activations