© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 83148
    Prev
    Next
    INDEX
    Explanations

    instances of the word "deliver" and its variations, indicating a focus on providing products or services effectively

    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
    uell
    -0.07
    ecial
    -0.07
    uld
    -0.06
    	Copyright
    -0.06
    itational
    -0.06
    ù
    -0.06
    emory
    -0.06
    izontal
    -0.06
    æľ
    -0.06
    ìĵ°
    -0.06
    POSITIVE LOGITS
    ables
    0.09
     deliver
    0.08
     goods
    0.08
    goods
    0.07
     Deliver
    0.07
    اÙĨس
    0.07
    querque
    0.07
     kepada
    0.07
    oha
    0.07
    atings
    0.07
    Activations Density 0.021%

    No Known Activations