© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 77938
    Prev
    Next
    INDEX
    Explanations

    phrases that refer to a history of achievements or accomplishments

    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
    ilk
    -0.08
    lsen
    -0.08
    ansa
    -0.07
    jiang
    -0.07
    quier
    -0.07
    apes
    -0.07
    Äįer
    -0.07
    tics
    -0.07
    ildo
    -0.07
    -coordinate
    -0.07
    POSITIVE LOGITS
    edly
    0.07
    rove
    0.07
    à¥ĩण
    0.06
    ed
    0.06
     of
    0.06
    RelativeTo
    0.06
    oa
    0.06
     dizzy
    0.06
     preced
    0.06
    578
    0.06
    Activations Density 0.008%

    No Known Activations