© 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. 126890
    Prev
    Next
    INDEX
    Explanations

    instances of the word "made" and its variations in contexts suggesting achievement or accomplishment

    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
    esso
    -0.06
    rome
    -0.06
    atie
    -0.06
    agen
    -0.06
     Merch
    -0.06
     wr
    -0.06
    bersome
    -0.06
    bir
    -0.06
    ocking
    -0.06
    alse
    -0.06
    POSITIVE LOGITS
     career
    0.08
     kari
    0.08
     Career
    0.07
     careers
    0.07
     reputation
    0.06
     Careers
    0.06
     history
    0.06
    semi
    0.06
    ä¼į
    0.06
    career
    0.06
    Activations Density 0.020%

    No Known Activations